EViews Help: Equation

coefpath display graphs of the paths of the coefficients plotted against lambda, fit measures, and estimation values in elastic net, ridge, Lasso, and variable selection using Lasso models.

coefscale scaled coefficients.

coint test for cointegration between series in an equation estimated using cointegrating regression.

cointgraph view a graph of the estimated cointegrating relation form of an ARDL estimated equation.

cointrel display information about the cointegrating relation specification and the coefficients in ARDL estimated equation.

cointrep view the estimated cointegration form and the long-run coefficients table of an ARDL estimated equation.

correl correlogram of the residuals.

correlsq correlogram of the squared residuals.

cvardecomp coefficient covariance decomposition table.

cvgraph display a graph of the cross-validation objective against the lambda path for elastic net, ridge, Lasso, and variable selection using Lasso models.

depfreq display frequency and cumulative frequency table for the dependent variable.

derivs derivatives of the equation specification.

didcs compute Callaway-Sant’Anna decomposition for difference-in-difference estimation.

didgbdecomp perform Goodman-Bacon decomposition for difference-in-difference estimation.

didtrends show difference-in-difference trends summary in graphical or tabular form.

display display table, graph, or spool in object window.

dynmult compute dynamic multipliers for long-run regressors in ARDL equations.

ecresults display the conditional error correction (CEC) and error correction (EC) regression results.

effects display table of estimated fixed and/or random effects.

endogtest perform the regressor endogeneity test.

facbreak factor breakpoint test for stability.

resoutliers detect outliers in the residuals or regressors of the equation.

fixedtest test significance of estimates of fixed effects for panel estimators.

funbias functional coefficients equation bias results.

funbw functional coefficients equation bandwidth results.

funci functional coefficients equation coefficient confidence intervals.

funcov functional coefficients covariance results.

funtest perform functional coefficients hypothesis and stability tests.

garch conditional standard deviation graph (only for equations estimated using ARCH).

grads examine the gradients of the objective function.

hettest test for heteroskedasticity.

hist histogram and descriptive statistics of the residuals.

icgraph display a graph of the selection criteria for the top 20 models observed as part of model selection during estimation.

ictable display a table of the log-likelihood and selection criteria for the top 20 models observed as part of model selection during estimation.

infbetas scaled difference in estimated betas for influence statistics.

infstats influence statistics.

instsum show a summary of the equation instruments.

label label information for the equation.

lambdacoefs display the spreadsheet of the matrix of coefficient values along the lambda path in elastic net, ridge, Lasso, and variable selection using Lasso models.

lambdaest display the table showing various values associated with estimation along the lambda path in elastic net, ridge, Lasso, and variable selection using Lasso models.

lambdafit display the table showing various fit statistics associated with estimates along the lambda path in elastic net, ridge, Lasso, and variable selection using Lasso models.

lambdapath display graphs of lambda against various fit and estimation measures in elastic net, ridge, Lasso, and variable selection using Lasso models.

lvageplot leverage plot.

means descriptive statistics by category of the dependent variable (only for binary, ordered, censored and count equations).

modselgraph display a graph of the selection criteria for the top 20 models for elastic net, ridge, Lasso, and variable selection using Lasso models.

modseltable display a table of the selection criteria and measures associated with the estimation and model selection of elastic net, ridge, Lasso, and variable selection using Lasso models.

multibreak perform multiple breakpoint testing for an equation specified by list and estimated by least squares.

newsimpact display a news-impact graph of equations estimated using GARCH.

nyblom perform the Nyblom test of parameter stability or structural change in equations estimated using GARCH.

orthogtest perform the instrument orthogonality test.

outliers display the outliers summary view for an equation estimated via least squares with automatic outlier indicator saturation.

output table of estimation results.

pmghausmantest displays a spool object with the results of the Hausman test for similarity against mean-group and dynamic fixed effects estimators in PMG estimation.

predict prediction (fit) evaluation table (only for binary and ordered equations).

qrcrprocess displays a spool object producing a quantile process of the cointegrating relation.

qrecprocess displays a spool object producing a quantile process for each of the conditional error correction and error correction coefficients.

qrprocess display table or graph of quantile process estimates.

qrslope test of equality of slope coefficients across multiple quantile regression estimates.

qrsymm test of coefficients using symmetric quantiles.

ranhaus Hausman test for correlation between random effects and regressors.

rcomptest tests for the presence of cross-sectional or time random components in a panel equation. estimated using pooled least squares.

representations text showing specification of the equation.

reset Ramsey’s RESET test for functional form.

resids display, in tabular form, the actual and fitted values for the dependent variable, along with the residuals.

resoutliers Detect outliers in the residuals or regressors of the equation.

results table of estimation results.

rgmprobs display the regime probabilities in a switching regression equation.

rls recursive residuals least squares (only for non-panel equations estimated by ordinary least squares, without ARMA terms).

signbias perform the Sign bias test (Engle and Ng, 1993) of misspecification in equations estimated using GARCH.

similarity compute Hausman tests for Pooled mean group ARDL equations.

srcoefs displays a spool object with the results of error-correction regressions for each cross-section in PMG estimation.

strconstant tests for constancy of the base specification coefficients against a smoothly varying alternative in a smooth threshold regression.

strlinear compute tests for linearity of the base specification against the smooth threshold alternative in a smooth threshold regression.

strnonlin compute various tests for additional additive or encapsulated nonlinearity in a smooth threshold regression.

strwgts compute and display the transition weights in a smooth threshold regression.

symmtest compute symmetry test for nonlinear distributed lag variables in nonlinear ARDL models.

testadd likelihood ratio test for adding variables to equation.

testdrop likelihood ratio test for dropping variables from equation.

testfit performs Hosmer and Lemeshow and Andrews goodness-of-fit tests (only for equations estimated using binary).

transprobs display the state transition probabilities in a switching regression equation.

ubreak Andrews-Quandt test for unknown breakpoint.

varinf display Variance Inflation Factors (VIFs).

wald Wald test for coefficient restrictions.

weakinst display the weak instruments summary.

white White test for heteroskedasticity.

Equation Procs

clearhist clear the contents of the history attribute.

clearremarks clear the contents of the remarks attribute.

copy creates a copy of the equation.

didmakeeq create an equation object with the underlying fixed-effects estimation of a difference-in-difference equation.

displayname set display name.

fit static forecast.

forecast dynamic forecast.

makecoint Create a series containing the estimated cointegrating relationship from an ARDL estimated equation.

makederivs make group containing derivatives of the equation specification.

makefunobj save coefficients, residuals, bias, variance, and confidence intervals for functional coefficients equations.

makegarch create conditional variance series (only for ARCH equations).

makegrads make group containing gradients of the objective function.

makelimits create vector of estimated limit points (only for ordered models).

makemodel create model from estimated equation.

makeregs make group containing the regressors.

makergmprobs save the regime probabilities in a switching regression equation.

makeresids make series containing residuals from equation.

makestrwgts save the smooth transition weights in a smooth threshold regression.

maketransprobs save the state transition probabilities in a switching regression equation.

olepush push updates to OLE linked objects in open applications.

setattr set the value of an object attribute.

setpilotbw compute and set the value of the local pilot bandwidth (for functional coefficients equations).

updatecoefs update coefficient vector(s) from equation.

Equation Data Members

Scalar Values

@aic Akaike information criterion.

@bylist returns 1 or 0 depending on whether the equation was estimated by list.

@coefcov(i,j) covariance of coefficient estimates i and j.

@coefs(i) i-th coefficient value.

@deviance deviance (for Generalized Linear Models).

@deviancestat deviance statistic: deviance divided by degrees-of-freedom (for Generalized Linear Models).

@df degrees-of-freedom for equation.

@dispersion estimate of dispersion (for Generalized Linear Models).

@dw Durbin-Watson statistic.

@f F-statistic.

@finalbw returns the final bandwidth used in functional coefficient estimation.

@fixeddisp indicator for whether the dispersion is a fixed value (for Generalized Linear Models).

@fprob probability value of the F-statistic.

@hacbw bandwidth for HAC estimation of GMM weighting matrix or long-run covariance in cointegrating regression (if applicable).

@hq Hannan-Quinn information criterion.

@instrank rank of instruments (if applicable).

@jstat J-statistic — value of the GMM objective function (for GMM and TSLS).

@jprob probability value of the J-statistic.

@lambdamin minimum lambda value from ENET cross-validation.

@limlk estimate of LIML

(if applicable).

@logl value of the log likelihood function.

@lrprob probability value of likelihood ratio statistic (if applicable).

@lrstat likelihood ratio statistic (if applicable).

@lrvar long-run variance estimate for cointegrating regression (if applicable).

@meandep mean of the dependent variable.

@nbreaks number of breaks in breakpoint least squares and thresholds in threshold regression.

@ncases number of cases.

@nclusters number of clusters used in computing cluster robust covariances.

@ncoef number of estimated coefficients.

@ncross number of cross-sections used in estimation (equal to 1 for non-panel workfiles).

@npers number of workfile periods used in estimation (same as @regobs for non-panel workfiles).

@nregimes number of regimes in a switching and breakpoint regression.

@nthresholds number of thresholds in threshold regression.

@ntreatment difference-in-difference number of cross sections receiving treatment.

@objective quasi-likelihood objective function (if applicable).

@pearsonssr Pearson sum-of-squared residuals (for Generalized Linear Models).

@pearsonstat Pearson statistic: Pearson SSR divided by degrees-of-freedom (for Generalized Linear Models).

@pilotbw returns the pilot bandwidth used in functional coefficient estimation.

@qlrprob probability value of quasi-likelihood ratio statistic (if applicable).

@qlrstat quasi-likelihood ratio statistic (if applicable).

@quantdep quantile of dependent variable (for quantile regression).

@r2 R-squared statistic.

@rbar2 adjusted R-squared statistic.

@rdeviance restricted (constant only) deviance (for Generalized Linear Models).

@regobs number of observations in regression.

@rlogl restricted (constant only) log-likelihood (if applicable).

@rmse root MSE.

@rn2 Rn-squared statistic.

@robf robust F-statistic (Wald-test form).

@robfprob robust F-statistic (Wald-test form) p-value.

@robjective restricted (constant only) quasi-likelihood objective function (if applicable).

@rw2 Rw-squared.

@schwarz Schwarz information criterion.

@sddep standard deviation of the dependent variable.

@se standard error of the regression.

@sparsity estimate of sparsity (for quantile regression).

@ssr sum of squared residuals.

@ssr2 second-stage SSR.

@stderrs(i) standard error for coefficient i.

@thresholds number of thresholds (for threshold regression).

@tstats(i) t-statistic or z-statistic value for coefficient i.

@wmeandep weighted mean of dependent variable (if applicable).

@wgtscale scaling factor for weights (if applicable).

c(i) i-th element of default coefficient vector for equation (if applicable).

Vectors and Matrices

@ardlceccoefs returns a vector of coefficient estimates from the conditional error-correction (CEC) regression in univariate (N)ARDL estimation.

@ardleccoefs returns a vector of coefficient estimates from the traditional error-correction (EC) regression in univariate (N)ARDL estimation.

@ardlcoint returns a coef containing coefficients from the cointegrating relationship form of an ARDL estimation.

@ardllrcoefs returns a coef containing coefficients from the long run relationship form of a non-panel ARDL estimation.

@ardlsrcoefs returns a matrix where each row corresponds to an individual cross-section’s short-run coefficients. Only applicable for PMG/ARDL estimation.

@ardlsrses returns a matrix where each row corresponds to an individual cross-section’s short-run coefficient standard errors. Only applicable for PMG/ARDL estimation.

@coefcov covariance matrix for coefficient estimates.

@coefs coefficient vector.

@contempcov symmetric matrix containing the contemporaneous covariance

for cointegrating regression residuals estimated with CCR.

@cvconverge Elastic net path cross-validation convergence test values (lambda values in rows; lambda in first column, training-test sample results in remaining columns).

@cvisvalid Elastic net path cross-validation valid results indicators (lambda values in rows; lambda in first column, training-test sample results in remaining columns).

@cviters Elastic net path cross-validation iterations (lambda values in rows; lambda in first column, training-test sample results in columns).

@cvobjective Elastic net path cross-validation objective values (lambda values in rows; lambda in first column, training-test sample results in remaining columns).

@effects vector of fixed and random effects estimates (if applicable).

@fcgrid returns a vector of unique grid values over which functional coefficients are evaluated in functional coefficient estimation.

@initprobs matrix containing initial probabilities for switching regression equations.

@instwgt symmetric matrix containing the final sample instrument weighting matrix used during GMM or TSLS estimation (e.g.,

for 2SLS and

for White weighting).

@lambdacoefs Elastic net lambda path coefficients matrix (lambda values in rows; variables in columns). Full set of variables including those with zero coefficients along the path.

@lambdaest Elastic net lambda path estimation measures matrix (lambda values in rows; columns contain the lambda values, number of non-zero coefficients, estimation objective, sums-of-squares portion of the objective,

portion of the objective,

portion of the objective).

@lambdafit Elastic net lambda path fit measures matrix (lambda values in rows; columns contain the lambda values, number of non-zero coefficients, R-squared, adjusted R-squared, and sums-of-squared residuals).

@lambdapath Elastic net lambda path vector.

@lambda2cov symmetric matrix

containing the long run covariances of

with

and

for cointegrating regression equations estimated with CCR and FMOLS.

@lrcov symmetric matrix containing the long-run covariance

for cointegrating regression equations estimated with CCR and FMOLS.

@modselresults Elastic net path model selection summary (lambda values in rows; lambda in first column, followed by model selection objective, number of non-zero coefficients, and the fit statistics (sum-of-squared residuals, mean-square error, R-squared, and adjusted R-squared) associated with the estimated model.

@pmgcxcoefs returns a matrix of coefficient estimates from the error-correction regressions for each cross-section in PMG estimation. Each column corresponds to a single cross-section and each column corresponds to a coefficient estimate from the traditional error-correction regression, in order of appearance.

@pmgcxses returns a matrix of coefficient standard error estimates from the error-correction regressions for each cross-section in PMG estimation. Each column corresponds to a single cross-section and each column corresponds to a coefficient standard error estimate from the traditional error-correction regression, in order of appearance.

@pmglrcoefs returns a vector of long-run (pooled) coefficient estimates in PMG estimation.

@pmgsrcoefs returns a vector of short-run (mean-group) coefficient estimates in PMG estimation.

@pvals vector containing the coefficient probability values.

@stderrs vector of standard errors for coefficients.

@thresholds vector of threshold values for threshold estimation.

@tstats vector of t-statistic or z-statistic values for coefficients.

String Values

@ardlcointsubst returns string representation of the cointegration form of an ARDL equation with substituted coefficients.

@attr("arg") string containing the value of the arg attribute, where the argument is specified as a quoted string.

@breaks string representation of the breakpoints in breakpoint least squares or thresholds in threshold regression.

@coeflabels coefficient labels used in regression output table.

@coeflist returns a string containing a space delimited list of the coefficients used in estimation (e.g., “C(1) C(2) C(3)”). This function always returns the list of actual coefficients used, irrespective of whether the original equation was specified by list or by expression.

@command full command line form of the estimation command. Note this is a combination of @method, @options and @spec.

@depends string containing a list of the series in the current workfile on which this equation depends.

@description string containing the Equation object’s description (if available).

@detailedtype returns a string with the object type: “EQUATION”.

@displayname returns the equation’s display name. If the equation has no display name set, the name is returned.

@esteq returns string representation of the estimation equation.

@extralist space delimited list of the equation's extra regressors. For equation's estimated by ARCH, @extralist contains the variance equation terms. For equations estimated by CENSORED, this contains the error distribution terms. For all other equation methods it returns an empty string.

@instlist space delimited list of the equation instruments (if applicable).

@method command line form of estimation method (“ARCH”, “LS”, etc....).

@name returns the name of the Equation.

@options command line form of estimation options.

@remarks string containing the equation object’s remarks (if available).

@smpl description of the sample specified for estimation.

@spec original equation specification. Note this will be different from @varlist if the equation specification contains groups, or is specified by expression.

@subst returns string representation of the equation with substituted coefficients.

@type returns a string with the object type: “EQUATION”.

@updatetime returns a string representation of the time and date at which the equation was last updated.

@varlist space delimited list of the equation’s dependent variable and regressors if the equation was specified by list, or the equation’s underlying variables (both dependent and independent) if the equation was specified by expression.

@varselkept space delimited list of variables kept by model selection.

@varselrejected space delimited list of the variables dropped by model selection.

Equation Examples

To apply an estimation method (proc) to an existing equation object:

equation ifunc

ifunc.ls r c r(-1) div

To declare and estimate an equation in one step, combine the two commands:

equation value.tsls log(p) c d(x) @ x(-1) x(-2)

equation drive.logit ifdr c owncar dist income

equation countmod.count patents c rdd

To estimate equations by list, using ordinary and two-stage least squares:

equation ordinary.ls log(p) c d(x)

equation twostage.tsls log(p) c d(x) @ x(-1) x(-2)

You can create and use other coefficient vectors:

coef(10) a

coef(10) b

equation eq01.ls y=c(10)+b(5)*y(-1)+a(7)*inc

The fitted values from EQ01 may be saved using,

series fit = eq01.@coefs(1) + eq01.@coefs(2)*y(‑1) + eq01.@coefs(3)*inc

or by issuing the command:

eq01.fit fitted_vals

To perform a Wald test:

eq01.wald a(7)=exp(b(5))

You can save the t-statistics and covariance matrix for your parameter estimates:

vector eqstats=eq01.@tstats

matrix eqcov=eq01.@coefcov

abtest

Equation Views

Test for serial correlation in a panel GMM equation using the Arellano-Bond test.

Tests for first and second order autocorrelation amongst the residuals of an equation estimated by GMM with first differences in a panel workfile. If the underlying errors are i.i.d, we would expect the first differences to be negatively first order serially correlated, and not display second order correlation.

Syntax

eq_name.abtest(options)

Options

p	Print output from the test.

Examples

equation eq1.gmm(cx=fd, per=f, gmm=perwhite, iter=oneb, levelper) n n(-1) n(-2) w w(-1) k ys ys(-1) @ @dyn(n,-2) w w(-1) k ys ys(-1)

eq1.abtest

estimates an equation using GMM with first difference fixed effects, and then tests for first and second order autocorrelation.

Cross-references

See “Arellano-Bond Serial Correlation Testing” for discussion.

arch	Equation Methods

Estimate generalized autoregressive conditional heteroskedasticity (GARCH) models.

Syntax

eq_name.arch(p,q,options) y [x1 x2 x3] [@ p1 p2 [@ t1 t2]]

eq_name.arch(p,q,options) y=expression [@ p1 p2 [@ t1 t2]]

The first two options specify the order of the GARCH model:

• The arch estimation method specifies a GARCH(p, q) model with p ARCH terms and q GARCH terms. Note the order of the arguments in which the ARCH and GARCH terms are entered.

The maximum value for

is 9; values above will be set to 9. The minimum value for

is 1. The minimum value for

is 0. If either

is not specified, EViews will assume a corresponding order of 1. Thus, a GARCH(1, 1) is assumed by default.

• For CGARCH, FIEGARCH and MIDAS-GARCH models, EViews only estimates (1,1) models. For these specifications,

and

options should not be specified, and if provided, will be ignored.

After the “ARCH” keyword and options, specify the dependent variable followed by a list of regressors in the mean equation.

• By default, only the intercept is included in the conditional variance equation. If you wish to specify variance regressors, list them after the mean equation using an “@”-sign to separate the mean from the variance equation.

• When estimating component ARCH models, you may specify exogenous variance regressors for both the permanent and transitory components. After the mean equation regressors, first list the regressors for the permanent component, followed by an “@”-sign, then the regressors for the transitory component. A constant term is always included as a permanent component regressor.

• For MIDAS-GARCH models, the low-frequency permanent component regressor are entered after the mean equation regressors and an “@”-sign. The regressor should be specified as pagename\seriesname.

Options

Type Options

The default is to estimate a standard GARCH model. You may specify one of the followings keywords to estimate a different model:

egarch	Exponential GARCH.
parch[=arg]	Power ARCH. If the optional arg is provided, the power parameter will be set to that value, otherwise the power parameter will be estimated.
cgarch	Component (permanent and transitory) ARCH.
figarch	Fractional GARCH (FIGARCH).
fiegarch	Fractional Exponential GARCH (FIEGARCH(1,1)).
midas	MIDAS GARCH(1,1)

General Options

thrsh	For Component GARCH models, include a threshold term.
thrsh=integer (default=0)	Number of threshold terms for GARCH models. The maximum number of terms allowed is 9.
vt	Variance target of the constant term for GARCH models. (May not be used with integrated specifications.)
integrated	Restrict GARCH model to be integrated, i.e. IGARCH. (May not be used with variance targeting.)
asy=integer (default=1)	Number of asymmetric terms in Power ARCH or EGARCH models. The maximum number of terms allowed is 9.
trunclag=integer (default=1000)	Number of terms in the expansion approximation for FIGARCH and FIEGARCH models.
archm=arg	ARCH-M (ARCH in mean) specification with the conditional standard deviation (“archm=sd”), the conditional variance (“archm=var”), or the log of the conditional variance (“archm= log”) entered as a regressor in the mean equation.
tdist [=number]	Estimate the model assuming that the residuals follow a conditional Student’s t-distribution (the default is the conditional normal distribution). Providing the optional number greater than two will fix the degrees of freedom to that value. If the argument is not provided, the degrees of freedom will be estimated.
ged [=number]	Estimate the model assuming that the residuals follow a conditional GED (the default is the conditional normal distribution). Providing a positive value for the optional argument will fix the GED parameter. If the argument is not provided, the parameter will be estimated.
z	Turn of backcasting for both initial MA innovations and initial variances.
backcast=n	Backcast weight to calculate value used as the presample conditional variance. Weight needs to be greater than 0 and less than or equal to 1; the default value is 0.7. Note that a weight of 1 is equivalent to no backcasting, i.e. using the unconditional residual variance as the presample conditional variance.
optmethod = arg	Optimization method: “bfgs” (BFGS); “newton” (Newton-Raphson), “opg” or “bhhh” (OPG or BHHH), “legacy” (EViews legacy). “bfgs” is the default for new equations.
optstep = arg	Step method: “marquardt” (Marquardt - default); “dogleg” (Dogleg); “linesearch” (Line search). (Applicable when “optmethod=bfgs”, “optmethod=newton” or “optmethod=opg”.)
b	Use Berndt-Hall-Hall-Hausman (BHHH) as maximization algorithm. The default is Marquardt. (Applicable when “optmethod=legacy”.)
cov=arg	Covariance method: “ordinary” (default method based on inverse of the estimated information matrix), “huber” or “white” (Huber-White sandwich method), “bollerslev” (Bollerslev-Wooldridge method).
covinfo = arg	Information matrix method: “opg” (OPG); “hessian” (observed Hessian), “ (Applicable when non-legacy “optmethod=” with “cov=ordinary”.)
h	Bollerslev-Wooldridge robust quasi-maximum likelihood (QML) covariance/standard errors. (Applicable for “optmethod=legacy” when estimating assuming normal errors.)
m=integer	Set maximum number of iterations.
c=scalar	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled coefficients.
s	Use the current coefficient values in “C” as starting values (see also param).
s=number	Specify a number between zero and one to determine starting values as a fraction of preliminary LS estimates (out of range values are set to “s=1”).
numericderiv / ‑numericderiv	[Do / do not] use numeric derivatives only. If omitted, EViews will follow the global default.
fastderiv / ‑fastderiv	[Do / do not] use fast derivative computation. If omitted, EViews will follow the global default. Available only for legacy estimation (“optmeth=legacy”).
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
prompt	Force the dialog to appear from within a program.
p	Print estimation results.

MIDAS Options

lag=arg	Specify the number of lags of the low frequency regressor to include. Default value is 32.
beta=arg	Beta function restriction: none (“none”), trend coefficient equals 1 (“trend”), endpoints coefficient equals 0 (“end-point”), both trend and endpoints restriction (“both”). For use when “midwgt=beta”. The default is “beta=none”.
thrsh	Include a threshold term.
optmethod=arg	Optimization method for nonlinear estimation: “bfgs” (BFGS); “newton” Newton-Raphson), “opg”, “bhhh” (OPG or BHHH), or “hybrid” (initial BHHH followed by BFGS). Hybrid is the default method.
optstep=arg	Step method for nonlinear estimation: “marquardt” (Marquardt); “dogleg” (Dogleg); “linesearch” (Line search). Marquardt is the default method.
cov=arg	Covariance method for nonlinear models: “ordinary” (default method based on inverse of the estimated information matrix), “huber” or “white” (Huber-White sandwich).
covinfo=arg	Information matrix method for nonlinear models: “opg” (OPG); “hessian” (observed Hessian).
nodf	Do not perform degree of freedom corrections in computing coefficient covariance matrix. The default is to use degree of freedom corrections.
m=integer	Set maximum number of iterations.
c=scalar	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled coefficients. The criterion will be set to the nearest value between 1e-24 and 0.2.
s	Use the current coefficient values in estimator coefficient vector as starting values in nonlinear estimation. If the “s=number” or “s” options are not used, EViews will use random starting values.
s=number	Determine starting values for nonlinear estimation. Specify a number between zero and oSpecify the number of lags of the low frequency regressor to include. Default value is 32.ne representing the fraction of preliminary EViews chosen values. Note that out of range values are set to “s=1”. Specifying “s=0” initializes coefficients to zero. If the “s=number” or “s” options are not used, EViews will use random starting values.
seed=positive integer from 0 to 2,147,483,647	Seed the random number generator used in random starting values. If not specified, EViews will seed random number generator with a single integer draw from the default global random number generator.
showopts/-showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
coef=arg	Specify the name of the coefficient vector; the default behavior is to use the “C” coefficient vector.
prompt	Force the dialog to appear from within a program.
p	Print estimation results.

Saved results

Most of the results saved for the ls estimation method are also available after ARCH estimation; see Equation::ls for details.

Examples

equation arc1.arch(4, 0, m=1000, cov=bollerslev) sp500 c

estimates an ARCH(4) model with a mean equation consisting of the series SP500 regressed on a constant. The procedure will perform up to 1000 iterations, and will report Bollerslev-Wooldridge robust QML standard errors upon completion.

The commands:

c = 0.1

equation arc1.arch(thrsh=1, s, mean=var) @pch(nys) c ar(1)

estimate a TARCH(1, 1)-in-mean specification with the mean equation relating the percent change of NYS to a constant, an AR term of order 1, and a conditional variance (GARCH) term. The first line sets the default coefficient vector to 0.1, and the “s” option uses these values as coefficient starting values.

The command:

equation arc1.arch(1, 2, asy=0, parch=1.5, ged=1.2) dlog(ibm)=c(1)+c(2)* dlog(sp500) @ r

estimates a symmetric Power ARCH(2, 1) (autoregressive GARCH of order 2, and moving average ARCH of order 1) model with GED errors. The power of model is fixed at 1.5 and the GED parameter is fixed at 1.2. The mean equation consists of the first log difference of IBM regressed on a constant and the first log difference of SP500. The conditional variance equation includes an exogenous regressor R.

Following estimation, we may save the estimated conditional variance as a series named GARCH1.

arc1.makegarch garch1

Cross-references

See “ARCH and GARCH Estimation” for a discussion of ARCH models. See also Equation::garch and Equation::makegarch.

archtest

Equation Views

Test for autoregressive conditional heteroskedasticity (ARCH).

Carries out Lagrange Multiplier (LM) tests for ARCH in the residuals of a single least squares equation.

Syntax

eq_name.archtest(options)

Options

You must specify the order of ARCH for which you wish to test. The number of lags to be included in the test equation should be provided in parentheses after the arch keyword.

Other Options:

prompt	Force the dialog to appear from within a program.
p	Print output from the test.

Examples

equation eq1.ls output c labor capital

eq1.archtest(4)

Regresses OUTPUT on a constant, LABOR, and CAPITAL, and tests for ARCH up to order 4.

equation eq1.arch sp500 c

eq1.archtest(4)

Estimates a GARCH(1,1) model with mean equation of SP500 on a constant and tests for additional ARCH up to order 4. Note that when performing an archtest as a view off of an estimated arch equation, EViews will use the standardized residuals (the residual of the mean equation divided by the estimated conditional standard deviation) to form the test.

Cross-references

See “ARCH LM Test” for further discussion of testing ARCH and “ARCH and GARCH Estimation” for a general discussion of working with ARCH models in EViews.

See also Equation::hettest for a more full-featured version of this test.

ardl	Equation Methods

Estimate an equation with autoregressive distributed lags using linear and nonlinear least squares or quantile regression.

Syntax

equation.ardl(options) linear_regs [@ static_regs] [@asy dual_asymmetric_regs] [@asylr long_run_asymmetric_regs] [@asysr short_run_asymmetric_regs]

The linear_regs specification is required:

• The linear_regs list should be the dependent variable followed by a list of linear distributed-lag regressors.

The remaining specifications are optional

• static_regs should be a list of static regressors, not including a constant or trend term.

• dual_asymmetric_regs are distributed-lag regressors which are asymmetric both in the short-run and long-run.

• long_run_asymmetric_regs regressors are distributed lag-regressors which are asymmetric in the long-run but symmetric in the short-run.

• short_run_asymmetric_regs are asymmetric regressors which are distributed lag-regressors which are asymmetric in the short-run but symmetric in the long-run.

You may specify the lag for an individual distributed-lag variable using the “@fl(variable, lag)” syntax. For instance, if the variable X should use 3 lags, irrespective of the fixed or automatic lag settings, you may specify this by entering “@fl(x, 3)” in the regressor list.

Options

Least Squares ARDL Options

method=arg (default = “ls”)	Set the method of estimation: "ls" (least-squares regression, default) or "qreg" (quantile regression).
determ=arg (default = “rconst”)	Johansen deterministic trend type: “none” (no deterministics), “rconst” (restricted constant and no trend), “uconst” (unrestricted constant and no trend), “rtrend” (unrestricted constant and restricted trend, “utrend” (unrestricted constant and unrestricted trend).
trend=arg (deprecated)	Johansen deterministic trend type: “none” (no deterministics), “const” (restricted constant and no trend, default), “uconst” (unrestricted constant and no trend), “linear” (unrestricted constant and restricted trend, “ulinear” (unrestricted constant and unrestricted trend). Note: this is a deprecated s option which handles a subset of cases covered by the “determ=” option
fixed	Do not use automatic selection for lag lengths. This option must be used with the “deplags=” and “reglags=” options.
deplags=int (default = 4)	Set the number of lags for the dependent variable to int. If automatic selection is used, this sets the maximum number of possible lags. If fixed lags are used (the fixed option is set), this fixes the number of lags.
reglags=int (default = 4)	Set the number of lags for the explanatory variables (dynamic regressors) to int. If automatic selection is used, this sets the maximum number of possible lags. If fixed lags are used (the fixed option is set), this fixes the number of lags for each regressor.
ic=key (default =“aic”)	Set the method of automatic model selection. key may take values of “aic” (Akaike information criterion, default), “bic” (Schwarz criterion), “hq” (Hannan-Quinn criterion) or “rbar2” (Adjusted R-squared, not applicable in panel workfiles).
cov=arg	Covariance method: “ordinary” (default method based on inverse of the estimated information matrix), “huber” or “white” (Huber-White sandwich method), “hac” (Newey-West HAC, available for nonlinear least squares or ARMA estimated by CLS)..
nodf	Do not perform degree of freedom corrections in computing coefficient covariance matrix. The default is to use degree of freedom corrections.
covlag=arg (default=1)	Whitening lag specification: integer (user-specified lag value), “a” (automatic selection).
covinfosel=arg (default=“aic”)	Information criterion for automatic selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn) (if “lag=a”).
covmaxlag=integer	Maximum lag-length for automatic selection (optional) (if “lag=a”). The default is an observation-based maximum of .
covkern=arg (default=“bart”)	Kernel shape: “none” (no kernel), “bart” (Bartlett, default), “bohman” (Bohman), “daniell” (Daniel), “parzen” (Parzen), “parzriesz” (Parzen-Riesz), “parzgeo” (Parzen-Geometric), “parzcauchy” (Parzen-Cauchy), “quadspec” (Quadratic Spectral), “trunc” (Truncated), “thamm” (Tukey-Hamming), “thann” (Tukey-Hanning), “tparz” (Tukey-Parzen).
covbw=arg (default=“fixednw”)	Kernel Bandwidth: “fixednw” (Newey-West fixed), “andrews” (Andrews automatic), “neweywest” (Newey-West automatic), number (User-specified bandwidth).
covnwlag=integer	Newey-West lag-selection parameter for use in nonparametric kernel bandwidth selection (if “covbw=neweywest”).
covbwint	Use integer portion of bandwidth.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
prompt	Force the dialog to appear from within a program.
p	Print results.

Quantile ARDL Options

quant=number (default = 0.5)	Quantile to be fit (where number is a value between 0 and 1).
w=arg	Weight series or expression. Note: we recommend that, absent a good reason, you employ the default settings Inverse std. dev. weights (“wtype=istdev”) with EViews default scaling (“wscale=eviews”) for backward compatibility with versions prior to EViews 7.
wtype=arg (default=“istdev”)	Weight specification type: inverse standard deviation (“istdev”), inverse variance (“ivar”), standard deviation (“stdev”), variance (“var”).
wscale=arg	Weight scaling: EViews default (“eviews”), average (“avg”), none (“none”). The default setting depends upon the weight type: “eviews” if “wtype=istdev”, “avg” for all others.
cov=arg (default=“sandwich”)	Method for computing coefficient covariance matrix: “iid” (ordinary estimates), “sandwich” (Huber sandwich estimates), “boot” (bootstrap estimates). When “cov=iid” or “cov=sandwich”, EViews will use the sparsity nuisance parameter calculation specified in “spmethod=” when estimating the coefficient covariance matrix.
bwmethod=arg (default = “hs”)	Method for automatically selecting bandwidth value for use in estimation of sparsity and coefficient covariance matrix: “hs” (Hall-Sheather), “bf” (Bofinger), “c” (Chamberlain).
bw =number	Use user-specified bandwidth value in place of automatic method specified in “bwmethod=”.
bwsize=number (default = 0.05)	Size parameter for use in computation of bandwidth (used when “bw=hs” and “bw=bf”).
spmethod=arg (default=“kernel”)	Sparsity estimation method: “resid” (Siddiqui using residuals), “fitted” (Siddiqui using fitted quantiles at mean values of regressors), “kernel” (Kernel density using residuals) Note: “spmethod=resid” is not available when “cov=sandwich”.
btmethod=arg (default= “pair”)	Bootstrap method: “resid” (residual bootstrap), “pair” (xy-pair bootstrap), “mcmb” (MCMB bootstrap), “mcmba” (MCMB-A bootstrap).
btreps=integer (default=100)	Number of bootstrap repetitions
btseed=positive integer	Seed the bootstrap random number generator. If not specified, EViews will seed the bootstrap random number generator with a single integer draw from the default global random number generator.
btrnd=arg (default=“kn” or method previously set using rndseed).	Type of random number generator for the bootstrap: improved Knuth generator (“kn”), improved Mersenne Twister (“mt”), Knuth’s (1997) lagged Fibonacci generator used in EViews 4 (“kn4”) L’Ecuyer’s (1999) combined multiple recursive generator (“le”), Matsumoto and Nishimura’s (1998) Mersenne Twister used in EViews 4 (“mt4”).
btobs=integer	Number of observations for bootstrap subsampling (when “bsmethod=pair”). Should be significantly greater than the number of regressors and less than or equal to the number of observations used in estimation. EViews will automatically restrict values to the range from the number of regressors and the number of estimation observations. If omitted, the bootstrap will use the number of observations used in estimation.
btout=name	(optional) Matrix to hold results of bootstrap simulations.
k=arg (default=“e”)	Kernel function for sparsity and coefficient covariance matrix estimation (when “spmethod=kernel”): “e” (Epanechnikov), “r” (Triangular), “u” (Uniform), “n” (Normal–Gaussian), “b” (Biweight–Quartic), “t” (Triweight), “c” (Cosinus).
m=integer	Maximum number of iterations.
s	Use the current coefficient values in estimator coefficient vector as starting values (see also param).
s=number (default =0)	Determine starting values for equations. Specify a number between 0 and 1 representing the fraction of preliminary least squares coefficient estimates. Note that out of range values are set to the default.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
prompt	Force the dialog to appear from within a program.
p	Print estimation results.

Examples

wfopen http://www.stern.nyu.edu/~wgreene/Text/Edition7/TableF5-2.txt

opens example data from Greene (2008, page 685), containing quarterly US macroeconomic variables between 1950 and 2000.

The following command

equation eq01.ardl(deplags=8, reglags=8) log(realcons) log(realgdp) @ @expand(@quarter, @droplast)

creates an equation object and estimates an ARDL model with the log of real consumption as the dependent variable, and the log of real GDP as a dynamic regressor. Quarterly dummy variables are included as static regressors. Automatic model selection is used to determine the number of lags of LOG(REALCONS) and LOG(REALGDP).

The command

equation eq02.ardl(deplags=3, reglags=3, fixed) log(realcons) log(realgdp) @ @expand(@quarter, @droplast)

estimates a second model, replicating Example 20.4 from Greene, with a fixed three lags of the dependent variable and three lags of the regressor.

equation eq03.ardl(deplags=1, reglags=1, fixed) log(realcons) log(realgdp) @asy log(realgovt)

The line above estimates an ARDL(1,1,1) model with the log of real consumption as the dependent variable, the log of real GDP as a linear regressor, and log of real government expenditures as a dual asymmetric regressor.

equation eq04.ardl(deplags=1, reglags=1, fixed) log(realcons) log(realgdp) @asy log(realgovt) @asysr log(realinvs)

extends the previous model and estimates an ARDL(1,1,1,1) model by including the log of real investments as a long-run asymmetric regressor.

equation eq05.ardl(deplags=1, reglags=1, fixed) log(realcons) log(realgdp) @asy log(realgovt) @asysr log(realinvs) @asylr log(tbilrate)

The line above extends the previous model and estimates an ARDL(1,1,1,1,1) model by including the log of treasury bill rates as a short-run asymmetric regressor.

wfopen oecd.wf1

equation eq06.ardl(fixed, deplags=1, reglags=1) log(cons) log(inf) log(inc)

This example estimates a panel ARDL model using the workfile “OECD.wf1”. This model replicates that given in the original Pesaran, Shin and Smith 1999 paper. Model selection is not used to choose the optimal lag lengths, rather a fixed single lag of both the dependent variable and the regressor is employed.

equation eq07.ardl(method=qreg, ls=fixed, deplags=1, reglags=1, quant=0.4) log(realcons) log(realgdp)

This command estimates a QARDL(1,1) model where lag selection is fixed for both the dependent and independent regressors, and the quantile value is 0.4.

Cross-references

See “ARDL and Quantile ARDL” for further discussion.

arma	Equation Views

Examine ARMA structure of estimated equation.

Provides diagnostic graphical and tabular views that aid you in assessing the structure of the ARMA component of an estimated equation. The view is currently available only for equations specified by list and estimated by least squares that include at least one AR or MA term. There are four views types available: roots, correlogram, impulse response, and frequency spectrum.

Syntax

eq_name.arma(type=arg [,options])

where eq_name is the name of an equation object specified by list, estimated by least squares, and contains at least one ARMA term.

Options

type=arg	Required “type=” option selects the type of ARMA structure output: “root” displays the inverse roots of the AR/MA characteristic polynomials, “acf” displays the second moments (autocorrelation and partial autocorrelation) for the data in the estimation sample and for the estimated model, “imp” displays the impulse responses., “freq” displays the frequency spectrum.
t	Displays the table view of the results for the view specified by the “type=” option. By default, EViews will display a graphical view of the ARMA results.
hrz=arg	Specifies the maximum lag length for “type=acf”, and the maximum horizon (periods) for “type=imp”.
imp=arg	Specifies the size of the impulse for the impulse response (“type=imp”) view. By default, EViews will use the regression estimated standard error.
save=arg	Stores the results as a matrix object with the specified name. The matrix holds the results roughly as displayed in the table view of the corresponding type. For “type=root”, roots for the AR and MA polynomials will be stored in separate matrices as NAME_AR and NAME_MA, where “NAME” is the name given by the “save=” option.
prompt	Force the dialog to appear from within a program.
p	Print the table or graph output.

Examples

eq1.arma(type=root, save=root)

displays and saves the ARMA roots from the estimated equation EQ1. The roots will be placed in the matrix object ROOT.

eq1.arma(type=acf, hrz=25, save=acf)

computes the second moments (autocorrelation and partial autocorrelations) for the observations in the sample and the estimated model. The results are computed for a 25 period horizon. We save the results in the matrix object ACF.

eq1.arma(type=imp, hrz=25, save=imp)

computes the 25 period impulse-response function implied by the estimated ARMA coefficients. EViews will use the default 1 standard error of the estimated equation as the shock, and will save the results in the matrix object IMP.

eq1.arma(type=freq)

displays the frequency spectrum in graph form.

Cross-references

See “ARMA Structure” for details. See also “Time Series Regression”.

auto	Equation Views

Compute serial correlation LM (Lagrange multiplier) test.

Carries out Breusch-Godfrey Lagrange Multiplier (LM) tests for serial correlation in the estimation residuals.

Syntax

eq_name.auto(order, options)

You must specify the order of serial correlation for which you wish to test. You should specify the number of lags in parentheses after the auto keyword, followed by any additional options.

Options

prompt	Force the dialog to appear from within a program.
p	Print output from the test.

Examples

To regress OUTPUT on a constant, LABOR, and CAPITAL, and test for serial correlation of up to order four you may use the commands:

equation eq1.ls output c labor capital

eq1.auto(4)

The commands:

output(t) c:\result\artest.txt

equation eq1.ls cons c y y(-1)

eq1.auto(12, p)

perform a regression of CONS on a constant, Y and lagged Y, and test for serial correlation of up to order twelve. The first line redirects printed tables/text to the ARTEST.TXT file.

Cross-references

See “Serial Correlation LM Test” for further discussion of the Breusch-Godfrey test.

binary

Equation Methods

Estimate binary dependent variable models.

Estimates models where the binary dependent variable Y is either zero or one (probit, logit, gompit).

Syntax

eq_name.binary(options) y x1 [x2 x3 ...]

eq_name.binary(options) specification

Options

d=arg (default=“n”)	Specify likelihood: normal likelihood function, probit (“n”), logistic likelihood function, logit (“l”), Type I extreme value likelihood function, Gompit (“x”).
optmethod = arg	Optimization method: “bfgs” (BFGS); “newton” (Newton-Raphson), “opg” or “bhhh” (OPG or BHHH), “legacy” (EViews legacy). Newton-Raphson is the default method.
optstep = arg	Step method: “marquardt” (Marquardt); “dogleg” (Dogleg); “linesearch” (Line search). Marquardt is the default method.
cov=arg	Covariance method: “ordinary” (default method based on inverse of the estimated information matrix), “huber” or “white” (Huber-White sandwich method), “glm” (GLM method), “cr” (cluster robust).
covinfo = arg	Information matrix method: “opg” (OPG); “hessian” (observed Hessian - default). (Applicable when non-legacy “optmethod=”.)
df	Degree-of-freedom correct the coefficient covariance estimate.(For non-cluster robust methods estimated using non-legacy estimation).
h	Huber-White quasi-maximum likelihood (QML) standard errors and covariances. (Legacy option applicable when “optmethod=legacy”).
g	GLM standard errors and covariances. (Legacy option applicable when “optmethod=legacy”).
crtype=arg (default “cr1”)	Cluster robust weighting method: “cr0” (no finite sample correction), “cr1” (finite sample correction), when “cov=cr”.
crname=arg	Cluster robust series name, when “cov=cr”.
m=integer	Set maximum number of iterations.
c=scalar	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled coefficients. The criterion will be set to the nearest value between 1e-24 and 0.2.
s	Use the current coefficient values in “C” as starting values (see also param).
s=number	Specify a number between zero and one to determine starting values as a fraction of EViews default values (out of range values are set to “s=1”).
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
prompt	Force the dialog to appear from within a program.
p	Print results.

Examples

To estimate a logit model of Y using a constant, WAGE, EDU, and KIDS, and computing Huber-White standard errors, you may use the command:

equation eq1.binary(d=l,cov=huber) y c wage edu kids

Note that this estimation uses the default global optimization options. The commands:

param c(1) .1 c(2) .1 c(3) .1

equation probit1.binary(s) y c x2 x3

estimate a probit model of Y on a constant, X2, and X3, using the specified starting values. The commands:

coef beta_probit = probit1.@coefs

matrix cov_probit = probit1.@coefcov

store the estimated coefficients and coefficient covariances in the coefficient vector BETA_PROBIT and matrix COV_PROBIT.

Cross-references

See “Binary Dependent Variable Models” for additional discussion.

boundstest

Equation Views

Perform the Pesaran, Shin and Smith (2001) bounds test of long-run relationships from an ARDL estimated equation.

This view displays a spool object with the ARDL bounds test diagnostics. The first table is a summary of the test along with statistic values. The second table summarizes the bound test critical values associated with the F-statistic. When appropriate (the deterministic case does not include a restricted constant (cases 3 and 5), a third table summarizes the bound test critical values associated with the t-statistic.

Syntax

eq_name.boundstest(options)

Options

p	Print output.

Examples

wfopen http://www.stern.nyu.edu/~wgreene/Text/Edition7/TableF5-2.txt

equation eq02.ardl(deplags=3, reglags=3, fixed) log(realcons) log(realgdp) @ @expand(@quarter, @droplast)

show eq02.boundstest

This example uses data from Greene (2008, page 685), containing quarterly US macroeconomic variables between 1950 and 2000. The first line of this example downloads the data set, the second line creates an equation object and estimates an ARDL model with the log of real consumption as the dependent variable. Three lags of the dependent variable, and three lags of the log of real GDP are used as dynamic regressors. Quarterly dummy variables are included as static regressors.

The final line performs the Pesaran, Shin and Smith (2001) bounds test to test for a long-run relationship between the log of real consumption and the log of real GDP.

Cross-references

See “ARDL and Quantile ARDL” for further discussion.

breakls

Equation Methods

Estimation by linear least squares regression with breakpoints.

Syntax

eq_name.breakls(options) y z1 [z2 z3 ...] [@nv x1 x2 x3 ...]

List the dependent variable first, followed by a list of the independent variables that have coefficients which are allowed to vary across breaks, followed optionally by the keyword @nv and a list of non-varying coefficient variables.

Options

Breakpoint Options

method=arg (default=“seqplus1”)	Breakpoint selection method: “seqplus1” (sequential tests of single versus breaks), “seqall” (sequential test of all possible versus breaks), “glob” (tests of global vs. no breaks), “globplus1” (tests of versus globally determined breaks), “globinfo” (information criteria evaluation),“user” (user-specified break dates).
select=arg	Sub-method setting (options depend on “method=”). (1) if “method=glob”: Sequential (“seq”) (default), Highest significant (“high”), (“udmax”), (“wdmax”). (2) if “method=globinfo”: Schwarz criterion (“bic” or “sic”) (default), Liu-Wu-Zidek criterion (“lwz”).
trim=arg (default=5)	Trimming percentage for determining minimum segment size (5, 10, 15, 20, 25).
maxbreaks=integer (default=5)	Maximum number of breakpoints to allow (not applicable if “method=seqall”).
maxlevels=integer (default=5)	Maximum number of break levels to consider in sequential testing (applicable when “method=sequall”).
breaks="arg"	User-specified break dates entered in double quotes. For use when “method=user”.
size=arg (default=5)	Test sizes for use in sequential determination and final test evaluation (10, 5, 2.5, 1) corresponding to 0.10, 0.05, 0.025, 0.01, respectively
heterr	Assume regimes specific error distributions in variance computation.
commondata	Assume a common distribution for the data across segments (only applicable if original equation is estimated with a robust covariance method, “heterr” is not specified).

General Options

w=arg	Weight series or expression.
wtype=arg (default=“istdev”)	Weight specification type: inverse standard deviation (“istdev”), inverse variance (“ivar”), standard deviation (“stdev”), variance (“var”).
wscale=arg	Weight scaling: EViews default (“eviews”), average (“avg”), none (“none”). The default setting depends upon the weight type: “eviews” if “wtype=istdev”, “avg” for all others.
cov=keyword	Covariance type (optional): “white” (White diagonal matrix), “hac” (Newey-West HAC).
nodf	Do not perform degree of freedom corrections in computing coefficient covariance matrix. The default is to use degree of freedom corrections.
covlag=arg (default=1)	Whitening lag specification: integer (user-specified lag value), “a” (automatic selection).
covinfosel=arg (default=“aic”)	Information criterion for automatic selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn) (if “lag=a”).
covmaxlag=integer	Maximum lag-length for automatic selection (optional) (if “lag=a”). The default is an observation-based maximum of .
covkern=arg (default=“bart”)	Kernel shape: “none” (no kernel), “bart” (Bartlett, default), “bohman” (Bohman), “daniell” (Daniel), “parzen” (Parzen), “parzriesz” (Parzen-Riesz), “parzgeo” (Parzen-Geometric), “parzcauchy” (Parzen-Cauchy), “quadspec” (Quadratic Spectral), “trunc” (Truncated), “thamm” (Tukey-Hamming), “thann” (Tukey-Hanning), “tparz” (Tukey-Parzen).
covbw=arg (default=“fixednw”)	Kernel Bandwidth: “fixednw” (Newey-West fixed), “andrews” (Andrews automatic), “neweywest” (Newey-West automatic), number (User-specified bandwidth).
covnwlag=integer	Newey-West lag-selection parameter for use in nonparametric kernel bandwidth selection (if “covbw=neweywest”).
covbwoffset=integer (default=0)	Apply integer offset to bandwidth chosen by automatic selection method (“bw=andrews” or “bw=neweywest”).
covbwint	Use integer portion of bandwidth chosen by automatic selection method (“bw=andrews” or “bw=neweywest”).
coef=arg	Specify the name of the coefficient vector; the default behavior is to use the “C” coefficient vector.
prompt	Force the dialog to appear from within a program.
p	Print basic estimation results.

Examples

equation eq1.breakls m1 c unemp

uses the Bai-Perron sequential

versus

tests to determine the optimal breaks in a model regressing M1 on the breaking variables C and UNEMP.

equation eq2.breakls(method=glob, select=high) m1 c unemp

uses the global Bai-Perron

versus none tests to determine the breaks. The selected break will be the highest significant number of breaks.

equation eq3.breakls(size=5, trim=10) m1 c unemp

lowers the sequential test size from 0.10 to 0.05, and raises the trimming to 10 percent.

equation eq4.breakls(method=user, breaks="1990q1 2010q4") m1 c @nv unemp

estimates the model with two user-specified break dates. In addition, the variable UNEMP is restricted to have common coefficients across the regimes.

Cross-references

See “Least Squares with Breakpoints” for discussion. See also “Multiple Breakpoint Tests”.

See Equation::multibreak for multiple breakpoint testing.

breakspec

Equation Views

Display the breakpoint specification results for an equation estimated using breakls.

Syntax

eq_name.breakspec

Options

p	Print basic estimation results.

Examples

equation eq1.breakls m1 c unemp

eq1.breakspec(p)

displays and prints the breakpoint determination results for the equation EQ1 estimated using Bai-Perron sequential

versus

tests to determine the optimal breaks.

Cross-references

See “Least Squares with Breakpoints” for discussion.

breaktest

Equation Views

Breakpoint test.

Carries out a breakpoint test for parameter stability in equations estimated using TSLS and GMM.

See chow for related tests in equations estimated using least squares.

Syntax

eq_name.breaktest obs1 [obs2 obs3....]

You must provide the breakpoint observations (using dates or observation numbers) to be tested. To specify more than one breakpoint, separate the breakpoints by a space.

Examples

The commands

equation eq1.gmm m1 c gdp cpi @ gdp(-1) cpi(-1)

eq1.breaktest 1960 1970

perform a GMM estimation of M1 on a constant, GDP and CPI, with lagged values of GDP and CPI used as instruments, and then perform a breakpoint test to test whether the parameter estimates for the periods prior to 1960, during the 1960s, and then after 1970 are stable.

Cross-references

See “GMM Breakpoint Test” for discussion.

cdtest

Equation Views

Test for the presence of cross-sectional dependence in the residuals of panels equations.

Computes the Breusch-Pagan (1980) LM, Pesaran (2004) scaled LM, Pesaran (2004) CD, and Baltagi, and Feng and Kao (2012) bias-corrected scaled LM test for the residuals of a panel or pool equation, or panel series.

Syntax

eq_name.cdtest

Options

p	Print test results

Examples

equation eq1.ls(cx=f) @log(gsp) c @log(p_cap) @log(pc) @log(emp) unemp

eq1.cdtest

will estimate a panel model using the fixed effect estimator (EQ1) and then will compute and display the panel residual dependence test results.

Cross-references

See “Panel Cross-section Dependence Test” for discussion.

cellipse

Equation Views

Confidence ellipses for coefficient restrictions.

The cellipse view displays confidence ellipses for pairs of coefficient restrictions for an equation object.

Syntax

eq_name.cellipse(options) restrictions

Enter the equation name, followed by a period, and the keyword cellipse. This should be followed by a list of the coefficient restrictions. Joint (multiple) coefficient restrictions should be separated by commas.

Options

ind=arg	Specifies whether and how to draw the individual coefficient intervals. The default is “ind=line” which plots the individual coefficient intervals as dashed lines. “ind=none” does not plot the individual intervals, while “ind=shade” plots the individual intervals as a shaded rectangle.
size= number (default=0.95)	Set the size (level) of the confidence ellipse. You may specify more than one size by specifying a space separated list enclosed in double quotes.
dist= arg	Select the distribution to use for the critical value associated with the ellipse size. The default depends on estimation object and method. If the parameter estimates are least-squares based, the distribution is used; if the parameter estimates are likelihood based, the distribution will be employed. “dist=f” forces use of the F-distribution, while “dist=c” uses the distribution.
prompt	Force the dialog to appear from within a program.
p	Print the graph.

Examples

The two commands:

eq1.cellipse c(1), c(2), c(3)

eq1.cellipse c(1)=0, c(2)=0, c(3)=0

both display a graph showing the 0.95-confidence ellipse for C(1) and C(2), C(1) and C(3), and C(2) and C(3).

eq1.cellipse(dist=c,size="0.9 0.7 0.5") c(1), c(2)

displays multiple confidence ellipses (contours) for C(1) and C(2).

Cross-references

See “Confidence Intervals and Confidence Ellipses” for discussion.

See also Equation::ardl.

ecresults

Equation Views

Display a spool object showing tables with the conditional error correction (CEC) and error correction (EC) regression results in ARDL equations.

Syntax

eq_name.ecresults(options)

Options

p	Print output.

Example

ardl_eq.ecresults

displays a spool object with the CEC and EC regressions from the ARDL equation ARDL_EQ.

Cross-references

See “ARDL and Quantile ARDL” for a discussion of ARDL equation models.

See also Equation::cointreg and Equation::cointrel.

effects

Equation Views

Display the estimates of the fixed and/or random effects.

The effects view of a panel equation shows the estimates of the fixed and/or random effects associated with the estimated equation. These effects are expressed as deviations from the overall intercept displayed in the main equation output..

Syntax

eq_name.effects

Options

p	Print view.

Examples

equation eq1.ls(cx=f) y c x1 x2

e1.effects

estimates the equation EQ1 with fixed effects, and displays a view showing the estimated cross-section deviations from the overall intercept.

Cross-references

See “Panel Estimation” for a discussion of panel equation estimation.

endogtest

Equation Views

Performs the regressor endogeneity test

The endogtest view of an equation carries out the Regressor Endogeneity/Donald-Wu Test for equations estimated via TSLS or GMM.

Syntax

eq_name.endogtest regressors

Options

prompt

Force the dialog to appear from within a program.

Regressors

A list of equation regressors to be tested for endogeneity. Note the regressors must have been included in the original equation.

Examples

equation eq1.gmm y c x1 x2 @ z1 z2 z3 z4

e1.endogtest x1

estimates an equation, called EQ1, and estimates it via GMM, and then performs the Endogeneity Test, where X1 is tested for endogeneity.

Cross-references

See “Regressor Endogeneity Test” for a discussion.

enet	Equation Methods

Estimation of an elastic net model, including options for Lasso and ridge regression.

Syntax

equation_name.enet(options) y x1 [x2 x3 ...] [@vw(...)]

List the dependent variable first, followed by a list of the independent variables. Use a “C” if you wish to include an unpenalized intercept term.

Note that PDL and ARMA terms are not permitted in elastic net specifications.

If you wish to specify regressors with an individual penalty weight

, or to place inequality restrictions on the coefficient values, you may do so using special expressions of the form:

@vw(series_name, weight_value)

@vw(series_name[, wgt=weight_value, cmin=coef_min, cmax=coef_max])

where weight_value is a non-negative value, coef_min is a non-positive minimum coefficient value, and coef_max is a non-negative maximum coefficient value.

There are two forms of the special expression.

In the abbreviated form, you specify the variable name followed by the penalty weight value.

In the more general form, you specify the variable name followed by one or more keyword expressions in arbitrary order, with the “wgt=” argument specifying the penalty weight, “cmin=” with a non-positive minimum coefficient value, and “cmax=” with a non-negative maximum coefficient value.

When specifying individual regressor behavior using @vw, keep in mind that:

• The special intercept variable “C” is always non-penalized and has an implicit weight

• Individual penalty weights may be also specified using a vector in the Individual lambda wgts. vector edit field on the Penalty dialog page (or using the command estimation option “lambdawgt=vector_name”). If the vector weights are specified and individual weights are specified using the @vw keyword, the vector weights will be applied first, followed by the individual variable weights.

• Individual coefficient limit values may also be specified using vectors in the Min values vector and Max values vector edit fields on the Options dialog page (or the command estimation options “coefmin=vector_name” and “coefmax=vector_name”). If vector coefficient limits are specified and individual regressor limits are specified using the @vw keyword, the vector limits will be applied first, followed by the individual limits weights.

EViews will normalize the individual penalty weights so that they sum to the number of coefficients.

Options

Specification Options

penalty=arg (default=“el”)	Type of threshold estimation: “enet” (elastic net), “ridge” (ridge), “lasso” (Lasso).
alpha=arg (default=“.5”)	Value of the mixing parameter. Must be a value from zero to one.
lambda=arg	Value(s) of the penalty parameter. Can be one or more numbers or vector objects.Values must be zero or greater. If left blank (default) EViews will generate a list.

Penalty Options

ytrans=arg (default=“none”)	Scaling of the dependent variable: “none” (none), “L1” (L1), “L2” (L2), “stdsmpl” (sample standard deviation), “stdpop” (population standard deviation), “minmax” (min-max).
xtrans=arg (default=“stdpop”)	Scaling of the regressor variables: “none” (none), “L1” (L1 norm), “L2” (L2 norm), “stdsmpl” (sample standard deviation), “stdpop” (population standard deviation), “minmax” (min-max).
nlambdas=integer (default=100)	Number of penalty values for EViews-supplied list.
lambdaratio=arg	Ratio of minimum to maximum lambda for EViews-supplied list. You may specify a value for the ratio parameter, or you may leave the edit field blank to let EViews specify a default value based on the number of observations and the number of potential regressors . By default, EViews will set the ratio to 0.001.
lambdawgt= vector_name	Vector of individual penalty weights, containing non-negative values sized to and matching the order of the variables in the specification. If a vector is provided and individual weights are specified using one or more @vw regressors, the vector weights will be applied first, then overwritten by the individual variable weights. For comparability purposes, we normalize the final weights so that they sum to where the number of non-zero .
nlambdamin=integer (default=5)	Minimum number of lambda values in the path before applying stopping rules.
minddev=arg (default=1e-05)	Minimum change in deviance fraction to continue estimation. Truncate path estimation if relative change in deviance is smaller than this value.
maxedev=arg (default=0.99)	Maximum of deviance explained fraction attained to terminate estimation. Truncate path estimation if fraction of null deviance explained is larger than this value.
maxvars=arg	Maximum number of regressors in the model. Truncate path estimation if the number of coefficients (including those for non-penalized variables like the intercept) reaches this value.
maxvarsratio=arg	Maximum number of regressors in the model as a fraction of the number of observations. Truncate path estimation if the number of coefficients (including those for non-penalized variables like the intercept) divided by the number of observations reaches this value.

Cross Validation Options

cvmethod=arg (default=“kfold_cv”)	Cross-validation method: “kfold” (k-fold), “simple” (simple split), “mcarlo” (Monte Carlo), “leavepout” (leave-P-out), “leave1out” (leave-1-out), “rolling” (rolling window), “expanding” (expanding window).
cvmeasure=arg (default=“mse”)	Cross-validation fit measure: “mse” (mean-squared error), “r2” (R‑squared), “mae” (mean absolute error), “mape” (mean absolute percentage error), “smape” (symmetric mean absolute percentage error).
cvnfolds=arg (default=5)	Number of folds for K-fold cross-validation. For “cvmethod=kfold”.
cvftrain=arg (default=0.8)	Proportion of data for split and Monte Carlo methods. For “cvmethod=simple” and “cvmethod=mcarlo”.
cvnreps=arg (default=1)	Number of Monte Carlo method repetitions. For “cvmethod=mcarlo”.
cvleaveout=arg (default=2)	Number of data points left out for leave-p-out method. For “cvmethod=leavepout”.
cvnwindows=arg (default=4)	Number of windows for rolling window cross-validation method. For “cvmethod=rolling”.
cvinitial=arg (default=12)	Number of initial data points in the training set for expanding cross-validation. For “cvmethod=expanding”.
cvpregap=arg (default=0)	Number of observations between end of training set and beginning of test set. For “cvmethod=simple”, “cvmethod=rolling” and “cvmethod=expanding”.
cvhorizon=arg (default=1)	Number of observation in the test set. For “cvmethod=rolling” and “cvmethod=expanding”.
cvpostgap=arg (default=0)	Number of observations between end of test set and beginning of next training set for rolling window or between end of test set and end of next training set for expanding window. For “cvmethod=rolling” and “cvmethod=expanding”

Random Number Options

seed=positive_integer from 0 to 2,147,483,647	Seed the random number generator. If not specified, EViews will seed random number generator with a single integer draw from the default global random number generator.
rnd=arg (default=“kn” or method previously set using rndseed).	Type of random number generator: improved Knuth generator (“kn”), improved Mersenne Twister (“mt”), Knuth’s (1997) lagged Fibonacci generator used in EViews 4 (“kn4”) L’Ecuyer’s (1999) combined multiple recursive generator (“le”), Matsumoto and Nishimura’s (1998) Mersenne Twister used in EViews 4 (“mt4”).

Other Options

coefmin= vector_name, number	Vector of individual coefficient minimum values, containing negative or missing values sized to and matching the order of the variables in the specification, or a negative value for the minimum for all coefficients. Missing values in the vector should be used to indicate that the coefficient is unrestricted. If a vector of values is provided and individual minimums are specified using one or more @vw regressors, the vector values will be applied first, then overwritten by the individual values.
coefmax= vector_name, number	Vector of individual coefficient maximum values, containing positive or missing values sized to and matching the order of the variables in the specification, or a positive value for the maximum for all coefficients. Missing values in the vector should be used to indicate that the coefficient is unrestricted. If a vector of values is provided and individual maximums are specified using one or more @vw regressors, the vector values will be applied first, then overwritten by the individual values.
maxit=integer	Maximum number of iterations.
conv=scalar	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled estimates. The criterion will be set to the nearest value between 1e-24 and 0.2.
w=arg	Weight series or expression.
wtype=arg (default=“istdev”)	Weight specification type: inverse standard deviation (“istdev”), inverse variance (“ivar”), standard deviation (“stdev”), variance (“var”).
wscale=arg	Weight scaling: EViews default (“eviews”), average (“avg”), none (“none”). The default setting depends upon the weight type: “eviews” if “wtype=istdev”, “avg” for all others.
estmethod=arg	Estimation method: “cov” (use covariance algorithm) or “naive” (use naive algorithm). Default is EViews automatic.
showopts / ‑showopts	[Do / do not] display estimation options in the output.
prompt	Force the dialog to appear from within a program.
p	Print basic results view after estimation.

Examples

The command

equation enet1.enet(xtrans=none, lambdaratio=.0001, cvseed=513255899) lpsa c lcavol lweight age lbph svi lcp gleason pgg45

estimates an elastic net model with

equal to the default of 0.9, no regressor or dependent variable scaling, automatically determined 100-element lambda path with minimum lambda of 0.0001 times the maximum value, using the default K-fold cross-validation with 5 folds with an MSE objective and a random generator seed of 513255899 to determine the optimal value.

Similarly,

equation lasso1.enet(penalty=lasso, lambdaratio=.0001, cvseed=513255899) lpsa c lcavol lweight age lbph svi lcp gleason pgg45

estimates a Lasso model with regressor population standard deviation scaling, with the remaining settings as before, while

equation ridge1.enet(penalty=ridge, lambdaratio=.0001, cvseed=513255899) lpsa c lcavol lweight age lbph svi lcp gleason pgg45

estimates the equivalent ridge regression specification.

The command

equation enet2.enet(alpha=0.75, lambdaratio=.0001, cvmethod=rolling, cvmeasure=smape) lpsa c lcavol lweight age_s lbph svi lcp gleason pgg45

estimates an elastic net model with

equal to the 0.75 using rolling window cross-validation and SMAPE cross-validation.

We may use the @vw specifications to assign individual penalties and coefficient restrictions

equation enet3.enet(alpha=0.75, lambdaratio=.0001, cvmethod=rolling, cvseed=513255899) lpsa c @vw(lcavol, cmax=.4) lweight age lbph svi lcp gleason @vw(pgg45, cmax=0.075, w=1.2)

estimates an elastic net model with the coefficient of LCAVOL restricted to be less than or equal to 0.4, and the coefficient of PGG45 having a relative penalty weight of 1.2, and a maximum value of 0.075.

Identical specifications may be estimated using vectors of penalty weights and coefficient restrictions,

vector(9) cmax = na

cmax(2) = 0.4

cmax(9) = 1.2

vector(9) lwgt = 1

lwgt(9) = 1.2

equation enet4.enet(alpha=0.75, coefmax=cmax, lambdawgt=lwgt, lambdaratio=.0001, cvmethod=rolling, cvseed=513255899) lpsa c lcavol lweight age lbph svi lcp gleason pgg45

and

vector(9) cmax = na

cmax(2) = 0.4

vector(9) lwgt = 1

lwgt(9) = 50

equation enet5.enet(alpha=0.75, coefmax=cmax, lambdawgt=lwgt, lambdaratio=.0001, cvmethod=rolling, cvseed=513255899) lpsa c lcavol lweight age lbph svi lcp gleason @vw(pgg45, cmax=0.075, w=1.2)

since the penalty weight for PGG45 in the vector is overwritten by the individual weight specified using the @vw.

Note that in neither case is the intercept penalized, even though the corresponding element of LWGT is equal to 1 since the specification of “C” is always implicitly treated as “@VW(C, 0)”.

Cross-references

See “Elastic Net and Lasso” for a discussion of elastic net, ridge regression, and Lasso models.

equation

Equation Declaration

Declare an equation object.

Syntax

equation eq_name

equation eq_name.method(options) specification

Follow the equation keyword with a name and an optional specification. If you wish to enter the specification, you should follow the new equation name with a period, an estimation method, and the equation specification. Valid estimation methods are given in “Equation Methods”. Refer to each method for a description of the available options.

Examples

equation cobdoug.ls log(y) c log(k) log(l)

declares and estimates an equation object named COBDOUG.

equation ces.ls log(y)=c(1)*log(k^c(2)+l^c(3))

declares an equation object named CES containing a nonlinear least squares specification.

equation demand.tsls q c p x @ x p(-1) gov

creates an equation object named DEMAND and estimates DEMAND using two-stage least squares with instruments X, lagged P, and GOV.

Cross-references

“Basic Regression Analysis” provides basic information on estimation and equation objects.

facbreak

Equation Views

Factor breakpoint test for stability.

Carries out a factor breakpoint test for parameter constancy.

Syntax

eq_name.facbreak(options) ser1 [ser2 ser3 ...] @ x1 x2 x3

You must provide one or more series to be used as the factors with which to split the sample into categories. To specify more than one factor, separate the factors by a space. If the equation is specified by list and contains no nonlinear terms, you may specify a subset of the regressors to be tested for a breakpoint after an “@” sign.

Options

p	Print the result of the test.

Examples

The commands:

equation ppp.ls log(spot) c log(p_us) log(p_uk)

ppp.facbreak season

perform a regression of the log of SPOT on a constant, the log of P_US, and the log of P_UK, and employ a factor breakpoint test to determine whether the parameters are stable through the different values of SEASON.

To test whether only the constant term and the coefficient on the log of P_US are “stable” enter the commands:

ppp.facbreak season @ c log(p_us)

Cross-references

See “Factor Breakpoint Test” for further discussion.

See also Equation::chow, Equation::breaktest, and Equation::rls.

fit	Equation Procs

Compute static forecasts or fitted values from an estimated equation.

When the regressor contains lagged dependent values or ARMA terms, fit uses the actual values of the dependent variable instead of the lagged fitted values. You may instruct fit to compare the forecasted data to actual data, and to compute forecast summary statistics.

Not available for equations estimated using ordered methods; use Equation::makemodel to create a model using the ordered equation results (see example below).

Syntax

eq_name.fit(options) yhat [y_se]

eq_name.fit(options) yhat [y_se y_var]

Following the fit keyword, you should type a name for the forecast series and, optionally, a name for the series containing the standard errors. For ARCH specifications, you may use the second form of the command, and optionally include a name for the conditional variance series.

Forecast standard errors are currently not available for binary, censored, and count models.

Options

Basic Options

d	In models with implicit dependent variables, forecast the entire expression rather than the normalized variable.
u	Substitute expressions for all auto-updating series in the equation.
g	Graph the fitted values together with the ±2 standard error bands.
ga	Graph the forecasts along with the actuals (if available).
e	Produce the forecast evaluation table.
i	Compute the fitted values of the index. Only for binary, censored and count models.
s	Ignore ARMA terms and use only the structural part of the equation to compute the fitted values.
n	Ignore coef uncertainty in standard error calculations that use them.
forcsmpl = smpl	Fit sample (optional). If forecast sample is not provided, the workfile sample will be employed.
f = arg (default= “actual”)	Out-of-fit-sample fill behavior: “actual” (fill observations outside the fit sample with actual values for the fitted variable), “na” (fill observations outside the fit sample with missing values).
prompt	Force the dialog to appear from within a program.
p	Print view.

Stochastic Options

Options for forecasting from a functional coefficients estimated equation.

stochastic = arg (default = “none”)	Stochastic method: “none” (none), “mca” (Monte Carlo –asymptotic), “mcbs” (Monte Carlo – bootstrap), “bs” (bootstrap).
reps = integer (default = 999)	Number of stochastic replications
lhr = arg (default = 0.1)	Lower historical range (number between 0 and upper historical range).
uhr = arg (default = 0.9)	Upper historical range (number between lower historical range and 1).
bsdep	Bootstrap only the dependent variable (not the functional coefficient variable).

Examples

equation eq1.ls cons c cons(-1) inc inc(-1)

eq1.fit c_hat c_se

genr c_up=c_hat+2*c_se

genr c_low=c_hat-2*c_se

line cons c_up c_low

The first line estimates a linear regression of CONS on a constant, CONS lagged once, INC, and INC lagged once. The second line stores the static forecasts and their standard errors as C_HAT and C_SE. The third and fourth lines compute the +/–2 standard error bounds. The fifth line plots the actual series together with the error bounds.

equation eq2.binary(d=l) y c wage edu

eq2.fit yf

eq2.fit(i) xbeta

genr yhat = 1-@clogit(-xbeta)

The first line estimates a logit specification for Y with a conditional mean that depends on a constant, WAGE, and EDU. The second line computes the fitted probabilities, and the third line computes the fitted values of the index. The fourth line computes the probabilities from the fitted index using the cumulative distribution function of the logistic distribution. Note that YF and YHAT should be identical.

Note that you cannot fit values from an ordered model. You must instead solve the values from a model. The following lines generate fitted probabilities from an ordered model:

equation eq3.ordered y c x z

eq3.makemodel(oprob1)

solve oprob1

The first line estimates an ordered probit of Y on a constant, X, and Z. The second line makes a model from the estimated equation with a name OPROB1. The third line solves the model and computes the fitted probabilities that each observation falls in each category.

Cross-references

To perform dynamic forecasting, use Equation::forecast. See Equation::makemodel and Model::solve for forecasting from systems of equations or ordered equations.

See “Forecasting from an Equation” for a discussion of forecasting in EViews and “Discrete and Limited Dependent Variable Models” for a discussion of forecasting from binary, censored, truncated, and count models.

fitoutliers

Equation Views

Detect outliers using the results of an estimated equation.

Use Tukey fences, mean/standard deviation fences, wavelet outliers, ARMA outliers or influence statistics to identify observations that may contain outliers.

Syntax

equation_name.resoutliers(options)

Options

sens=arg	Set the sensitivity level. Valid arguments are “low”, “medium” (default), and “high”.
nofence	Do not perform Tukey and mean/standard deviation fences.
nowave	Do not perform Wavelet Outlier detection.
noarma	Do not perform ARMA based outlier detection. ARMA outlier detection is only available for least squares equations containing ARMA terms, and is turned on by default.
noinf	Do not perform influence statistic (not including DFBETAS) based outlier detection. Influence statistic outlier detection is only available for linear least squares equations, and is turned on by default.
dfbeta	Perform DFBETA influence statistic based outlier detection. DFBETA based outlier detection is only available for linear least squares equations, and is turned off by default.
tukeyk=arg	Set the value k in the Tukey fence detection routine. This will override the value of k set by the sens= option.
meanstdevk=arg	Set the value k in the mean/standard deviation fence detection routine. This will override the value of k set by the sens= option.
wavesig=arg	Set the value false discovery rate significance value used in the Wavelet Outlier detection routine. This will override the value set by the sens= option.
armac=arg	Set the value c in the ARMA outlier detection routine. This will override the value of c set by the sens= option.
rsbound=arg	Set the value c in RSTUDENT outlier detection. This will override the value of c set by the sens= option.
hbound=arg	Set the value c in HatMatrix outlier detection. This will override the value of c set by the sens= option.
dfsbound=arg	Set the value c in DFFITS outlier detection. This will override the value of c set by the sens= option.
covbound=arg	Set the value c in CovRatio outlier detection. This will override the value of c set by the sens= option.
betabound=arg	Set the value c in DFBETA outlier detection. This will override the value of c set by the sens= option.
series=name	Create a new series in the workfile, named name, containing a value of 1 for any observations identified as an outlier, and a value of 0 for any observation identified as not an outlier.
datestring=name	Create a new string object in the workfile containing the dates (or observation identifiers) for any observations identified as an outlier.
grlabels	Turn on observation labels on the outlier graph.
prompt	Force the dialog to appear from within a program.
p	Print results.

Examples

equation eq01.ls gdpc1 c unemp

eq01.resoutliers(nofence, dfbeta, sens=low)

Estimates an equation with GDPC1 as the dependent variable, and a constant and UNEMP as regressors. Then, outlier detection on the residuals is performed, opting to not use either fence detection, but to include the dfbeta influence statistics (along with the other influence statistics included by default), and setting the sensitivity of the detection to "low".

Cross-references

See “Outlier Detection” for discussion. See also Series::outliers.

fixedtest

Equation Views

Test joint significance of the fixed effects estimates.

Tests the hypothesis that the estimated fixed effects are jointly significant using

and LR test statistics. If the estimated specification involves two-way fixed effects, three separate tests will be performed; one for each set of effects, and one for the joint effects.

Syntax

eq_name.fixedtest(options)

Options

p	Print output from the test.

Examples

equation eq1.ls(cx=f) sales c adver lsales

eq1.fixedtest

estimates a specification with cross-section fixed effects and tests whether the fixed effects are jointly significant.

Cross-references

See “Fixed Effects Testing” for discussion.

See also Equation::rcomptest for testing random for random components.

forecast

Equation Procs

Computes dynamic forecasts of an estimated equation.

forecast computes the forecast for all observations in a specified sample. In some settings, you may instruct forecast to compare the forecasted data to actual data, and to compute summary statistics.

Syntax

eq_name.forecast(options) yhat [y_se]

eq_name.forecast(options) yhat [y_se y_var]

Enter a name for the forecast series and, optionally, a name for the series containing the standard errors. For ARCH specifications, you may use the second form of the command, and optionally enter a name for the conditional variance series. Forecast standard errors are currently not available for binary or censored models. forecast is not available for models estimated using ordered methods.

Options

d	In models with implicit dependent variables, forecast the entire expression rather than the normalized variable.
u	Substitute expressions for all auto-updating series in the equation.
g	Graph the forecasts together with the ±2 standard error bands.
ga	Graph the forecasts along with the actuals (if available).
e	Produce the forecast evaluation table.
i	Compute the forecasts of the index. Only for binary, censored and count models.
s	Ignore ARMA terms and use only the structural part of the equation to compute the forecasts.
n	Ignore coef uncertainty in standard error calculations that use them.
b =arg	MA backcast method: “fa” (forecast available). Only for equations estimated with MA terms. This option is ignored if you specify the “s” (structural forecast) option. The default method uses the estimation sample.
forcsmpl=smpl	Forecast sample (optional). If forecast sample is not provided, the workfile sample will be employed
f = arg (default= “actual”)	Out-of-forecast-sample fill behavior: “actual” (fill observations outside the forecast sample with actual values for the fitted variable), “na” (fill observations outside the forecast sample with missing values).
stochastic	Perform stochastic simulation for dynamic equations estimated using least squares.
streps=integer (default=1000)	Number of stochastic repetitions (for threshold regression or stochastic simulation).
stfrac=number (default=.02)	Fraction of failed repetitions before stopping (for threshold regression or stochastic simulation).
prompt	Force the dialog to appear from within a program.
p	Print view.

Examples

The following lines:

smpl 1970q1 1990q4

equation eq1.ls con c con(-1) inc

smpl 1991q1 1995q4

eq1.fit con_s

eq1.forecast con_d

plot con_s con_d

estimate a linear regression over the period 1970Q1–1990Q4, compute static (fitted) and dynamic forecasts for the period 1991Q1–1995Q4, and plot the two forecasts in a single graph.

equation eq1.ls m1 gdp ar(1) ma(1)

eq1.forecast m1_bj bj_se

eq1.forecast(s) m1_s s_se

plot bj_se s_se

estimates an ARMA(1,1) model, computes the forecasts and standard errors with and without the ARMA terms, and plots the two forecast standard errors.

Cross-references

To perform static forecasting with equation objects see Equation::fit. For multiple equation forecasting, see Equation::makemodel, and Model::solve.

For more information on equation forecasting in EViews, see “Forecasting from an Equation”.

funbias

Equation Views

Display functional coefficients bias results in graphical form.

For equations estimated using the functional coefficients method.

Syntax

eq_name.funbias(options)

Options

Basic Options

nolocalbw	Do not use the existing local pilot bandwidth (if it exists). Note that this option is only available if a local pilot bandwidth has been set previously, either through the estimation step, using the setpilotbw proc, or through another view or proc which set the local bandwidth.
p	Print output.

Pilot Bandwidth Options

If a local pilot bandwidth exists, all of the pilot bandwidth computation options below will be ignored unless the “nolocalbw” option is specified.

noupdate	Do not update the local pilot bandwidth using the current pilot bandwidth computation.
plth =arg (default = “cv”)	Pilot bandwidth method: simple rule-of-thumb (“rot”), robust rule-of-thumb (“rotr”), residual squares criterion (“rsc”), modified multi cross-validation (“cv”), user-defined (“user”).
pltbw=arg (default =1)	User-defined bandwidth (if “plth=user”).
plthmin=arg (default = 0.1)	Bandwidth grid search minimum value (if not “plth=user”).
plthmax=arg (default =1)	Bandwidth grid search maximum value (if not “plth=user”).
plthlen=integer (default = 100)	Bandwidth grid search length (if not “plth=user”).
plthinc=integer (default = 10)	Bandwidth grid search increment step percentage increase (if not “plth=user”).
plthcup=integer (default = 10)	Stop rule: consecutive increases of objective function before stop (not available when “plth=user”).
pltm=arg (default = 10)	Modified multifold CV m-value: percentage of sample size used in bandwidth determination (when “plth=cv”).
pltq=integer (default = 4)	Modified multifold CV Q-value: percentage of sample size used in bandwidth determination (when “plth=cv”).
auxk=integer (default = 2)	Estimation polynomial degree for pilot stage in excess of final stage degree. This number should always be an even positive integer.

Examples

eq1.funbias(p)

displays and prints a graph of the functional bias results for each functional coefficient computed using the existing local pilot bandwidth if present, or estimating the pilot bandwidth, if not. If estimated, the local pilot bandwidth is updated with the result.

eq1.funbias(nolocalbw, noupdate, plth=rsc)

ignores an existing local pilot bandwidth and instead computes a pilot bandwidth using the residual squares criterion. The existing saved local pilot bandwidth is retained.

Cross-references

See “Functional Coefficient Regression” for discussion of functional coefficients estimation See “Functional Bias” for discussion of bias.

See also Equation::makefunobj and Equation::setpilotbw.

funbw

Equation Views

Display functional coefficients final bandwidth selection results.

For equations estimated using the functional coefficients method.

Syntax

eq_name.funbw(options)

Options

Basic Options

pilot	Display pilot bandwidths.
graph	Display results in graphical form.
p	Print output.

Examples

eq1.funbw

displays the bandwidth results in table form.

eq1.funbw(graph, p)

displays and prints a graph of the estimation final bandwidth selection results.

eq1.funbw(pilot)

displays a table for results for the estimation and local pilot bandwidths.

Cross-references

See “Functional Coefficient Regression” for discussion of functional coefficients estimation. See “Bandwidth Selection” and “Bandwidth Views” for discussion of bandwidths.

See also Equation::funcoef and Equation::setpilotbw.

funci

Equation Views

Display graphs showing estimated lower and upper functional confidence intervals for the functional coefficients.

For equations estimated using the functional coefficients method.

Syntax

eq_name.funci(options) ci_level

where ci_level is a value between 0 and 1 specifying the confidence level you wish to display. If ci_level is omitted, EViews will use 0.95.

Options

Basic Options

nolocalbw	Do not use the existing local pilot bandwidth (if it exists). Note that this option is only available if a local pilot bandwidth has been set previously, either through the estimation step, using Equation::setpilotbw, or through another view or proc which sets the local bandwidth.
p	Print output.

Confidence Interval Options

seband	Produce standard error bands instead of confidence intervals.
sewidth =integer (default = 1)	Number of standard errors to use as half-width of confidence band (when “seband” is specified).
nobias	Ignore bias in confidence interval determination.

Pilot Bandwidth Options

If a local pilot bandwidth exists, all of the pilot bandwidth computation options below will be ignored unless the “nolocalbw” option is specified.

noupdate	Do not update the local pilot bandwidth using the current pilot bandwidth computation.
plth =arg (default = “cv”)	Pilot bandwidth method: simple rule-of-thumb (“rot”), robust rule-of-thumb (“rotr”), residual squares criterion (“rsc”), modified multi cross-validation (“cv”), user-defined (“user”).
pltbw=arg (default =1)	User-defined bandwidth (if “plth=user”).
plthmin=arg (default = 0.1)	Bandwidth grid search minimum value (if not “plth=user”).
plthmax=arg (default =1)	Bandwidth grid search maximum value (if not “plth=user”).
plthlen=integer (default = 100)	Bandwidth grid search length (if not “plth=user”).
plthinc=integer (default = 10)	Bandwidth grid search increment step percentage increase (if not “plth=user”).
plthcup=integer (default = 10)	Stop rule: consecutive increases of objective function before stop (not available when “plth=user”).
pltm=arg (default = 10)	Modified multifold CV m-value: percentage of sample size used in bandwidth determination (when “plth=cv”).
pltq=integer (default = 4)	Modified multifold CV Q-value: percentage of sample size used in bandwidth determination (when “plth=cv”).
auxk=integer (default = 2)	Estimation polynomial degree for pilot stage in excess of final stage degree. This number should always be an even positive integer.

Examples

eq1.funci 0.95 0.99

displays a graph of the 95% and 99% confidence intervals computed using the existing local pilot bandwidth if present, or estimating the pilot bandwidth, if not. If estimated, the local pilot bandwidth is updated with the result.

eq1.funci(seband, sewidth=3)

displays and prints a graph of the +/–3 confidence intervals.

The saved local pilot bandwidth is updated with the resulting bandwidth.

eq1.funci(nolocalbw, noupdate, plth=rsc) 0.9

ignores an existing local pilot bandwidth and instead computes a pilot bandwidth using the residual squares criterion and uses it in a 90% confidence interval calculation. The existing saved local pilot bandwidth is retained.

Cross-references

See “Functional Coefficient Regression” for discussion of functional coefficients estimation. See “Confidence Intervals” for discussion of functional confidence intervals.

See also Equation::makefunobj and Equation::setpilotbw.

funcoef

Equation Methods

Estimate a functional coefficient regression equation.

Syntax

eq_name.funcoef(options) y x1 [x2 x3 ...] @ funcoef_series

List the funcoef keyword, the dependent variable and a list of the regressor variables, followed by the “@” symbol and the name of the functional coefficient series.

Options

Basic Options

kern=arg (default=“epan”)	Kernel type: “epan” (Epanechnikov, default), “trngl” (Triangular), “unif” (Uniform), “gauss” (Normal–Gaussian), “bi” (Biweight–Quartic), “tri” (Triweight).
eval=arg (default=“data”)	Evalution points: observed data (“data”), grid of values (“grid”). if “eval=grid” you must specify the grid values using “gmin=”, “gmax=” and “glen=”, or using “gvec=”.
gmin = arg	Estimation grid minimum (if “eval=grid”). Must be specified along with “gmax=” and “glen=”.
gmax = arg	Estimation grid maximum (if “eval=grid”). Must be specified along with “gmin=” and “glen=”.
glen = arg	Estimation grid length (if “eval=grid”). Must be specified along with “gmin=” and “gmax=”.
gvec = arg	Estimation grid points in a vector object (if “eval=grid”).
plyk = arg (default = 1)	Estimation polynomial degree for final stage.
auxk = arg (default = 2)	Estimation polynomial degree for pilot stage in excess of final stage.
p	Print results.

Pilot Bandwidth Options

plth =arg (default = “cv”)	Pilot bandwidth method: simple rule-of-thumb (“rot”), robust rule-of-thumb (“rotr”), residual squares criterion (“rsc”), modified multi cross-validation (“cv”), user-defined (“user”).
pltbw=arg (default =1)	User-defined bandwidth (if “plth=user”).
plthmin=arg (default = 0.1)	Bandwidth grid search minimum value (if not “plth=user”).
plthmax=arg (default =1)	Bandwidth grid search maximum value (if not “plth=user”).
plthlen=integer (default = 100)	Bandwidth grid search length (if not “plth=user”).
plthinc=integer (default = 10)	Bandwidth grid search increment step percentage increase (if not “plth=user”).
plthcup=integer (default = 10)	Stop rule: consecutive increases of objective function before stop (not available when “plth=user”).
pltm=arg (default = 10)	Modified multifold CV m-value: percentage of sample size used in bandwidth determination (when “plth=cv”).
pltq=integer (default = 4)	Modified multifold CV Q-value: percentage of sample size used in bandwidth determination (when “plth=cv”).

Final Bandwidth Options

fnlh =arg (default = “cv”)	Final bandwidth method: simple rule-of-thumb (“rot”), robust rule-of-thumb (“rotr”), residual squares criterion (“rsc”), modified multi cross-validation (“cv”), integrated asymptotic mean square error (“mse”), leave-one-out cross-validation (“loo”), nonparametric AIC (“aic”), user-defined (“user”).
fnlbw=arg	User-defined bandwidth (if “fnlh=user”).
fnlhmin=arg (default = 0.1)	Bandwidth grid search minimum value (if not “fnlh=user”).
fnlhmax=arg (default =1)	Bandwidth grid search maximum value (if not “fnlh=user”).
fnlhlen=integer (default = 100)	Bandwidth grid search length (if not “fnlh=user”).
fnlhinc=integer (default = 10)	Bandwidth grid search increment step percentage increase (if not “fnlh=user”).
fnlhcup=integer (default = 10)	Stop rule: consecutive increases of objective function before stop (if not “fnlh=user”).
fnlm=arg (default = 10)	Modified multifold CV m-value: percentage of sample size used in bandwidth determination (when “fnlh=cv”).
fnlfq=integer (default = 4)	Modified multifold CV Q-value: percentage of sample size used in bandwidth determination (when “fnlh=cv”).

Examples

We consider examples for three equations that estimate FCOEF using UNRATE as the dependent variable, UNRATE(-1 to -2) as independent variables, and LWAGE(-4) as the functional coefficient variable.

eq.funcoef(eval=grid, gmin=0, gmax=10, glen=100) unrate unrate(-1) unrate(-2) @ lwage(-4)

evaluates over a custom uniform grid from 0 to 10 with length 100.

eq.funcoef(eval=grid, gvec=vecgrid) unrate unrate(-1) unrate(-2) @ lwage(-4)

evaluates over a custom grid provided by the values of a workfile vector called VECGRID.

eq.funcoef(plyk=3, auxk=5) unrate unrate(-1) unrate(-2) @ lwage(-4)

estimates using local polynomial fitting with main polynomial degree 3 and auxiliary polynomial degree 5. The latter is employed deriving bias, variance, and bandwidths.

Cross-references

See “Functional Coefficient Regression” for additional discussion of functional coefficients estimation.

funcov

Equation Views

Display functional coefficient covariance functions in graphical form.

For equations estimated using the functional coefficients method.

Syntax

eq_name.funcov(options)

Options

Basic Options

corr	Produce correlations instead of covariances.
nolocalbw	Do not use the existing local pilot bandwidth (if it exists) Note that this option is only available if a local pilot bandwidth has been set previously, either through the estimation step, using Equation::setpilotbw, or through another view or proc which sets the local bandwidth.
p	Print output.

Pilot Bandwidth Options

If a local pilot bandwidth has exists, all of the pilot bandwidth computation options below will be ignored unless the “nolocalbw” option is specified.

noupdate	Do not update the local pilot bandwidth using the current pilot bandwidth computation.
plth =arg (default = “cv”)	Pilot bandwidth method: simple rule-of-thumb (“rot”), robust rule-of-thumb (“rotr”), residual squares criterion (“rsc”), modified multi cross-validation (“cv”), user-defined (“user”).
pltbw=arg (default =1)	User-defined bandwidth (if “plth=user”).
plthmin=arg (default = 0.1)	Bandwidth grid search minimum value (if not “plth=user”).
plthmax=arg (default =1)	Bandwidth grid search maximum value (if not “plth=user”).
plthlen=integer (default = 100)	Bandwidth grid search length (if not “plth=user”).
plthinc=integer (default = 10)	Bandwidth grid search increment step percentage increase (if not “plth=user”).
plthcup=integer (default = 10)	Stop rule: consecutive increases of objective function before stop (not available when “plth=user”).
pltm=arg (default = 10)	Modified multifold CV m-value: percentage of sample size used in bandwidth determination (when “plth=cv”).
pltq=integer (default = 4)	Modified multifold CV Q-value: percentage of sample size used in bandwidth determination (when “plth=cv”).
auxk=integer (default = 2)	Estimation polynomial degree for pilot stage in excess of final stage degree. This number should always be an even positive integer.

Examples

eq1.funcov

displays the functional covariances computed using the existing local pilot bandwidth if present, or estimating the pilot bandwidth, if not. If estimated, the local pilot bandwidth is updated with the result.

eq1.funcov(corr, p)

displays and prints a graph of the correlation results.

eq1.funcov(nolocalbw, noupdate, auxk=4, plth=rsc)

ignores an existing local pilot bandwidth and instead computes a pilot bandwidth using the residual squares criterion and auxiliary degree of 4, and uses it in the covariance calculation. The existing saved local pilot bandwidth is retained.

Cross-references

See “Functional Coefficient Regression” for discussion of functional coefficients estimation. See “Functional Covariance/Correlation Matrix” for discussion of functional covariances.

See also Equation::makefunobj and Equation::setpilotbw.

funtest

Equation Views

Perform functional coefficients hypothesis and stability tests.

Test one or more functional coefficients for stability or equality with values in a specified series.

For equations estimated using the functional coefficients method.

Syntax

eq_name.funtest(options) arg

where arg is a comma separated list of functional coefficient restrictions for which you wish separately to test.

The coefficient restrictions

coefspec = restriction

where coefspec is a coefficient spec consisting of,

• c(k)

• @all

for individual coefficient k, and all coefficients, respectively, and restriction takes the form:

• series_name or vector

• scalar

• @constant

Options

Basic Options

nolocalbw	Do not use the existing local pilot bandwidth (if it exists) Note that this option is only available if a local pilot bandwidth has been set previously, either through the estimation step, using Equation::setpilotbw, or through another view or proc which sets the local bandwidth.
p	Print output.

Pilot Bandwidth Options

If a local pilot bandwidth has exists, all of the pilot bandwidth computation options below will be ignored unless the “nolocalbw” option is specified.

noupdate	Do not update the local pilot bandwidth using the current pilot bandwidth computation.
plth =arg (default = “cv”)	Pilot bandwidth method: simple rule-of-thumb (“rot”), robust rule-of-thumb (“rotr”), residual squares criterion (“rsc”), modified multi cross-validation (“cv”), user-defined (“user”).
pltbw=arg (default =1)	User-defined bandwidth (if “plth=user”).
plthmin=arg (default = 0.1)	Bandwidth grid search minimum value (if not “plth=user”).
plthmax=arg (default =1)	Bandwidth grid search maximum value (if not “plth=user”).
plthlen=integer (default = 100)	Bandwidth grid search length (if not “plth=user”).
plthinc=integer (default = 10)	Bandwidth grid search increment step percentage increase (if not “plth=user”).
plthcup=integer (default = 10)	Stop rule: consecutive increases of objective function before stop (not available when “plth=user”).
pltm=arg (default = 10)	Modified multifold CV m-value: percentage of sample size used in bandwidth determination (when “plth=cv”).
pltq=integer (default = 4)	Modified multifold CV Q-value: percentage of sample size used in bandwidth determination (when “plth=cv”).
auxk=integer (default = 2)	Estimation polynomial degree for pilot stage in excess of final stage degree. This number should always be an even positive integer.

Examples

eq1.funtest @all=10, c(2)=2, c(3)=y

performs three separate tests for the restrictions: all of the coefficients are constant and equal to 10, c(2) is a constant equal to 2, and c(3) is equal to the series Y using an existing local pilot bandwidth if present, or estimating the pilot bandwidth, if not. If estimated, the local pilot bandwidth is updated with the result.

eq1.funtest(nolocalbw, noupdate, auxk=4, plth=rsc) @all=3, c(2)=2, c(3)=y

ignores an existing local pilot bandwidth and instead computes a pilot bandwidth using the residual squares criterion and auxiliary degree of 4, and uses it in the test calculation. The existing saved local pilot bandwidth is retained.

Cross-references

See “Functional Coefficient Regression” for discussion of functional coefficients estimation. See “Stability and Significance Tests” for discussion of functional covariances.

See also Equation::makefunobj and Equation::setpilotbw.

garch

Equation Views

Conditional variance/covariance of (G)ARCH estimation.

Displays the conditional variance, covariance or correlation of an equation estimated by ARCH.

Syntax

eq_name.garch(options)

Options

v	Display conditional variance graph instead of the standard deviation graph.
p	Print the graph

Examples

equation eq1.arch sp500 c

eq1.garch

estimates a GARCH(1,1) model and displays the estimated conditional standard deviation graph.

eq1.garch(v, p)

displays and prints the estimated conditional variance graph.

Cross-references

ARCH estimation is described in “ARCH and GARCH Estimation”.

glm	Equation Methods

Estimate a Generalized Linear Model (GLM).

Syntax

eq_name.glm(options) spec

List the glm keyword, followed by the dependent variable and a list of the explanatory variables, or an explicit linear expression.

If you enter an explicit linear specification such as “Y=C(1)+C(2)*X”, the response variable will be taken to be the variable on the left-hand side of the equality (“Y”) and the linear predictor will be taken from the right-hand side of the expression (“C(1)+C(2)*X”).

Offsets may be entered directly in an explicit linear expression or they may be entered as using the “offset=” option.

Specification Options

family=arg (default=“normal”)	Distribution family: Normal (“normal”), Poisson (“poisson”), Binomial Count (“binomial”), Binomial Proportion (“binprop”), Negative Binomial (“negbin”), Gamma (“gamma”), Inverse Gaussian (“igauss”), Exponential Mean (“emean)”, Power Mean (“pmean”), Binomial Squared (“binsq”). The Binomial Count, Binomial Proportion, Negative Binomial, and Power Mean families all require specification of a distribution parameter:
n=arg (default=1)	Number of trials for Binomial Count (“family=binomial”) or Binomial Proportions (“family=binprop”) families.
fparam=arg	Family parameter value for Negative Binomial (“family=negbin”) and Power Mean (“family=pmean”) families.
link=arg (default=“identity”)	Link function: Identity (“identity”), Log (“log”), Log Compliment (“logc”), Logit (“logit”), Probit (“probit”), Log-log (“loglog”), Complementary Log-log (“cloglog”), Reciprocal (“recip”), Power (“power”), Box-Cox (“boxcox”), Power Odds Ratio (“opow”), Box-Cox Odds Ratio (“obox”). The Power, Box-Cox, Power Odds Ratio, and Box-Cox Odds Ratio links all require specification of a link parameter specified using “lparam=”.
lparam=arg	Link parameter for Power (“link=power”), Box-Cox (“link=boxcox”), Power Odds Ratio (“link=opow”) and Box-Cox Odds Ratio (“link=obox”) link functions.
offset=arg	Offset terms.
disp=arg	Dispersion estimator: Pearson statistic (“pearson”), deviance statistic (“deviance”), unit (“unit”), user-specified (“user”). The default is family specific: “unit” for Binomial Count, Binomial Proportion, Negative Binomial, and Poison, and “pearson” for all others. The “deviance” option is only offered for families in the exponential family of distributions (Normal, Poisson, Binomial Count, Binomial Proportion, Negative Binomial, Gamma, Inverse Gaussian).
dispval=arg	User-dispersion value (if “disp=user”).
fwgts=arg	Frequency weights.
w=arg	Weight series or expression.
wtype=arg (default=“istdev”)	Weight specification type: inverse standard deviation (“istdev”), inverse variance (“ivar”), standard deviation (“stdev”), variance (“var”).
wscale=arg	Weight scaling: EViews default (“eviews”), average (“avg”), none (“none”). The default setting depends upon the weight type: “eviews” if “wtype=istdev”, “avg” for all others.

In addition to the specification options, there are options for estimation and covariance calculation.

Additional Options

optmethod = arg	Optimization method: “bfgs” (BFGS); “newton” (Newton-Raphson), “opg” or “bhhh” (OPG or BHHH), “fisher” (IRLS – Fisher Scoring), “legacy” (EViews legacy). Newton-Raphson is the default method.
optstep = arg	Step method: “marquardt” (Marquardt); “dogleg” (Dogleg); “linesearch” (Line search). Marquardt is the default method.
estmeth=arg (default=”marquardt”)	Legacy estimation algorithm: Quadratic Hill Climbing (“marquardt”), Newton-Raphson (“newton”), IRLS - Fisher Scoring (“irls”), BHHH (“bhhh”). (Applicable when “optmethod=legacy”.)
m=integer	Set maximum number of iterations.
c=scalar	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled coefficients. The criterion will be set to the nearest value between 1e-24 and 0.2.
s	Use the current coefficient values in estimator coefficient vector as starting values (see also param).
s=number	Specify a number between zero and one to determine starting values as a fraction of EViews default values (out of range values are set to “s=1”).
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
preiter=arg (default=0)	Number of IRLS pre-iterations to refine starting values (only available for non-IRLS estimation).
cov=arg	Covariance method: “ordinary” (default method based on inverse of the estimated information matrix), “huber” or “white” (Huber-White sandwich method), “glm” (GLM method), “cr” (cluster robust).
covinfo = arg	Information matrix method: “opg” (OPG); “hessian” (observed Hessian), “fisher” (expected Hessian). (Applicable when “optmethod=” not equal to “legacy”.
nodf	Do not degree-of-freedom correct the coefficient covariance estimate.(For non-cluster robust methods).
covlag=arg (default=1)	Whitening lag specification: integer (user-specified lag value), “a” (automatic selection). Applicable where “cov=hac”.
covinfosel=arg (default=”aic”)	Information criterion for automatic selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn) (if “lag=a”). For settings where “cov=hac, covlag=a”.
covmaxlag=integer	Maximum lag-length for automatic selection (optional) (if “lag=a”). The default is an observation-based maximum of . For settings where “cov=hac, covlag=a”.
covkern=arg (default=“bart”)	Kernel shape: “none” (no kernel), “bart” (Bartlett, default), “bohman” (Bohman), “daniell” (Daniel), “parzen” (Parzen), “parzriesz” (Parzen-Riesz), “parzgeo” (Parzen-Geometric), “parzcauchy” (Parzen-Cauchy), “quadspec” (Quadratic Spectral), “trunc” (Truncated), “thamm” (Tukey-Hamming), “thann” (Tukey-Hanning), “tparz” (Tukey-Parzen). For settings where “cov=hac”.
covbw=arg (default=“fixednw”)	Kernel Bandwidth: “fixednw” (Newey-West fixed), “andrews” (Andrews automatic), “neweywest” (Newey-West automatic), number (User-specified bandwidth). For settings where “cov=hac” and “covkern=” is specified.
covnwlag=integer	Newey-West lag-selection parameter for use in nonparametric kernel bandwidth selection (if “covbw=neweywest”). For settings where “cov=hac” and “covkern=” is specified.
covbwoffset=number	Apply offset to automatically selected bandwidth. For settings where “cov=hac”, “covkern=” is specified, and “covbw=” is not user-specified.
covbwint	Use integer portion of kernel bandwidth. For settings where “cov=hac” and “covkern=” is specified.
crtype=arg (default “cr1”)	Cluster robust weighting method: “cr0” (no finite sample correction), “cr1” (finite sample correction), when “cov=cr”.
crname=arg	Cluster robust series name, when “cov=cr”.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
prompt	Force the dialog to appear from within a program.
p	Print results.

Examples

equation eqstrike.glm(link=log) numb c ip feb

estimates a normal regression model with exponential mean.

equation eqbinom.glm(family=binomial, n=total) disease c snore

estimates a binomial count model with default logit link where TOTAL contains the number of binomial trials and DISEASE is the number of binomial successes. The specification

equation eqbinom.glm(family=binprop, n=total, cov=huber, nodf) disease/total c snore

estimates the same specification in proportion form, and computes the coefficient covariance using the Huber-White sandwich with no d.f. correction.

equation eqprate.glm(family=binprop, disp=pearson) prate mprate log(totemp) log(totemp)^2 age age^2 sole

estimates a binomial proportions model with default logit link, but computes the coefficient covariance using the GLM scaled covariance with dispersion computed using the Pearson Chi-square statistic.

equation eqprate.glm(family=binprop, link=probit, cov=huber) prate mprate log(totemp) log(totemp)^2 age age^2 sole

estimates the same basic specification, but with a probit link and Huber-White standard errors.

equation testeq.glm(family=poisson, offset=log(pyears)) los hmo white type2 type3 c

estimates a Poisson specification with an offset term LOG(PYEARS).

Cross-references

See “Generalized Linear Models” for discussion.

gmm	Equation Methods

Estimation by generalized method of moments (GMM).

The equation object must be specified with a list of instruments.

Syntax

eq_name.gmm(options) y x1 [x2 x3...] @ z1 [z2 z3...]

eq_name.gmm(options) specification @ z1 [z2 z3...]

Follow the name of the dependent variable by a list of regressors, followed by the “@” symbol, and a list of instrumental variables which are orthogonal to the residuals. Alternatively, you can specify an expression using coefficients, an “@” symbol, and a list of instrumental variables. There must be at least as many instrumental variables as there are coefficients to be estimated.

In panel settings, you may specify dynamic instruments corresponding to predetermined variables. To specify a dynamic instrument, you should tag the instrument using “@DYN”, as in “@DYN(X)”. By default, EViews will use a set of period-specific instruments corresponding to lags from -2 to “-infinity”. You may also specify a restricted lag range using arguments in the “@DYN” tag. For example, to use lags from-5 to “-infinity” you may enter “@DYN(X, -5)”; to specify lags from -2 to -6, use “@DYN(X, -2, -6)” or “@DYN(X, -6, -2)”.

Note that dynamic instrument specifications may easily generate excessively large numbers of instruments.

Options

Non-Panel GMM Options

Basic GMM Options

Estimation Weighting Matrix Options

Covariance Options

Basic GMM Options

nocinst	Do not include automatically a constant as an instrument.
method=keyword	Set the weight updating method. keyword should be one of the following: “nstep” (N-Step Iterative, or Sequential N-Step Iterative, default), “converge” (Iterate to Convergence or Sequential Iterate to Convergence), “simul” (Simultaneous Iterate to Convergence), “oneplusone” (One-Step Weights Plus One Iteration), or “cue” (Continuously Updating”.
gmmiter=integer	Number of weight iterations. Only applicable if the “method=nstep” option is set.
w=arg	Weight series or expression.
wtype=arg (default=“istdev”)	Weight specification type: inverse standard deviation (“istdev”), inverse variance (“ivar”), standard deviation (“stdev”), variance (“var”).
wscale=arg	Weight scaling: EViews default (“eviews”), average (“avg”), none (“none”). The default setting depends upon the weight type: “eviews” if “wtype=istdev”, “avg” for all others.
m=integer	Maximum number of iterations.
s	Use the current coefficient values in estimator coefficient vector as starting values for equations specified by list (see also param).
s=number	Determine starting values for equations specified by list. Specify a number between zero and one representing the fraction of preliminary TSLS estimates computed without AR or MA terms to be used. Note that out of range values are set to “s=1”. Specifying “s=0” initializes coefficients to zero. By default EViews uses “s=1”. Does not apply to coefficients for AR and MA terms which are instead set to EViews determined default values.
c=number	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled coefficients. The criterion will be set to the nearest value between 1e-24 and 0.2.
l=number	Set maximum number of iterations on the first-stage iteration to get the one-step weighting matrix.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
numericderiv / ‑numericderiv	[Do / do not] use numeric derivatives only. If omitted, EViews will follow the global default.
fastderiv / ‑fastderiv	[Do / do not] use fast derivative computation. If omitted, EViews will follow the global default.
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
prompt	Force the dialog to appear from within a program.
p	Print results.

Estimation Weighting Matrix Options

instwgt=keyword	Set the estimation weighting matrix type. Keyword should be one of the following: “tsls” (two-stage least squares), “white” (White diagonal matrix), “hac” (Newey-West HAC, default) or “user” (user defined).
instwgtmat=name	Set the name of the user-defined estimation weighting matrix. Only applicable if the “instwgt=user” option is set.
instlag=arg (default=1)	Whitening Lag specification: integer (user-specified lag value), “a” (automatic selection).
instinfosel=arg (default=“aic”)	Information criterion for automatic whitening lag selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn) (if “instlag=a”).
instmaxlag= integer	Maximum lag-length for automatic selection (optional) (if “instlag=a”). The default is an observation-based maximum of .
instkern=arg (default=“bart”)	Kernel shape: “none” (no kernel), “bart” (Bartlett, default), “bohman” (Bohman), “daniell” (Daniell), “parzen” (Parzen), “parzriesz” (Parzen-Riesz), “parzgeo” (Parzen-Geometric), “parzcauchy” (Parzen-Cauchy), “quadspec” (Quadratic Spectral), “trunc” (Truncated), “thamm” (Tukey-Hamming), “thann” (Tukey-Hanning), “tparz” (Tukey-Parzen).
instbw=arg (default=“fixednw”)	Kernel Bandwidth: “fixednw” (Newey-West fixed), “andrews” (Andrews automatic), “neweywest” (Newey-West automatic), number (User-specified bandwidth).
instnwlag=integer	Newey-West lag-selection parameter for use in nonparametric bandwidth selection (if “instbw=neweywest”).
instbwoffset=integer (default=0)	Apply integer offset to bandwidth chosen by automatic selection method (“bw=andrews” or “bw=neweywest”).
instbwint	Use integer portion of bandwidth chosen by automatic selection method (“bw=andrews” or “bw=neweywest”).

Covariance Options

cov=keyword	Covariance weighting matrix type (optional): “updated” (estimation updated), “tsls” (two-stage least squares), “white” (White diagonal matrix), “hac” (Newey-West HAC), “wind” (Windmeijer) “cr” (cluster robust). or “user” (user defined). The default is to use the estimation weighting matrix.
nodf	Do not perform degree of freedom corrections in computing coefficient covariance matrix. The default is to use degree of freedom corrections. (For non-cluster robust methods).
covlag=arg (default=1)	Whitening lag specification: integer (user-specified lag value), “a” (automatic selection).
covinfosel=arg (default=”aic”)	Information criterion for automatic selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn) (if “lag=a”).
covmaxlag=integer	Maximum lag-length for automatic selection (optional) (if “lag=a”). The default is an observation-based maximum of .
covkern=arg (default=“bart”)	Kernel shape: “none” (no kernel), “bart” (Bartlett, default), “bohman” (Bohman), “daniell” (Daniel), “parzen” (Parzen), “parzriesz” (Parzen-Riesz), “parzgeo” (Parzen-Geometric), “parzcauchy” (Parzen-Cauchy), “quadspec” (Quadratic Spectral), “trunc” (Truncated), “thamm” (Tukey-Hamming), “thann” (Tukey-Hanning), “tparz” (Tukey-Parzen).
covbw=arg (default=“fixednw”)	Kernel Bandwidth: “fixednw” (Newey-West fixed), “andrews” (Andrews automatic), “neweywest” (Newey-West automatic), number (User-specified bandwidth).
covnwlag=integer	Newey-West lag-selection parameter for use in nonparametric kernel bandwidth selection (if “covbw=neweywest”).
covbwoffset=integer (default=0)	Apply integer offset to bandwidth chosen by automatic selection method (“bw=andrews” or “bw=neweywest”).
covbwint	Use integer portion of bandwidth chosen by automatic selection method (“bw=andrews” or “bw=neweywest”).
crtype=arg (default “cr1”)	Cluster robust weighting method: “cr0” (no finite sample correction), “cr1” (finite sample correction), when “cov=cr”.
crname=arg	Cluster robust series name, when “cov=cr”.

Panel GMM Options

cx=arg	Cross-section effects method: (default) none, fixed effects estimation (“cx=f”), first-difference estimation (“cx=fd”), orthogonal deviation estimation (“cx=od”)
per=arg	Period effects method: (default) none, fixed effects estimation (“per=f”).
levelper	Period dummies always specified in levels (even if one of the transformation methods is used, “cx=fd” or “cx=od”).
wgt=arg	GLS weighting: (default) none, cross-section system weights (“wgt=cxsur”), period system weights (“wgt=persur”), cross-section diagonal weighs (“wgt=cxdiag”), period diagonal weights (“wgt=perdiag”).
gmm=arg	GMM weighting: 2SLS (“gmm=2sls”), White period system covariances (Arellano-Bond 2-step/n-step) (“gmm=perwhite”), White cross-section system (“gmm=cxwhite”), White diagonal (“gmm=stackedwhite”), Period system (“gmm=persur”), Cross-section system (“gmm=cxsur”), Period heteroskedastic (“cov=perdiag”), Cross-section heteroskedastic (“gmm=cxdiag”). By default, uses the identity matrix unless estimated with first difference transformation (“cx=fd”), in which case, uses (Arellano-Bond 1-step) difference weighting matrix. In this latter case, you should specify 2SLS weights (“gmm=2sls”) for Anderson-Hsiao estimation.
cov=arg	Coefficient covariance method: (default) ordinary, White cross-section system robust (“cov=cxwhite”), White period system robust (“cov=perwhite”), White heteroskedasticity robust (“cov=stackedwhite”), Cross-section system robust/PCSE (“cov=cxsur”), Period system robust/PCSE (“cov=persur”), Cross-section heteroskedasticity robust/PCSE (“cov=cxdiag”), Period heteroskedasticity robust (“cov=perdiag”).
keepwgts	Keep full set of GLS/GMM weights used in estimation with object, if applicable (by default, only weights which take up little memory are saved).
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
iter=arg (default=“onec”)	Iteration control for GLS and GMM weighting specifications: perform one weight iteration, then iterate coefficients to convergence (“iter=onec”), iterate weights and coefficients simultaneously to convergence (“iter=sim”), iterate weights and coefficients sequentially to convergence (“iter=seq”), perform one weight iteration, then one coefficient step (“iter=oneb”).
s	Use the current coefficient values in estimator coefficient vector as starting values for equations specified by list (see also param).
s=number	Determine starting values for equations specified by list. Specify a number between zero and one representing the fraction of preliminary TSLS estimates computed without AR terms to be used. Note that out of range values are set to “s=1”. Specifying “s=0” initializes coefficients to zero. By default EViews uses “s=1”. Does not apply to coefficients for AR terms which are instead set to EViews determined default values.
m=integer	Maximum number of iterations.
c=number	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled coefficients. The criterion will be set to the nearest value between 1e-24 and 0.2.
l=number	Set maximum number of iterations on the first-stage iteration to get the one-step weighting matrix.
unbalsur	Compute SUR factorization in unbalanced data using the subset of available observations for a cluster.
numericderiv / ‑numericderiv	[Do / do not] use numeric derivatives only. If omitted, EViews will follow the global default.
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
prompt	Force the dialog to appear from within a program.
p	Print results.

Note that some options are only available for a subset of specifications.

Examples

In a non-panel workfile, we may estimate equations using the standard GMM options. The specification:

gmmc.gmm(instwgt=white,gmmiter=2,nodf) cons c y y(-1) w @ c p(-1) k(-1) x(-1) tm wg g t

estimates the Klein equation for consumption using GMM with a White diagonal weighting matrix (two steps and no degree of freedom correction). The command:

gmmi.gmm(method=cue,instwgt=hac,instlag=1,instkern=thann,instbw=andrews,nodf) i c y y(-1) k(-1) @ c p(-1) k(-1) x(-1) tm wg g t

estimates the Klein equation for investment using a Newey-West HAC weighting matrix, with pre-whitening with 1 lag, a Tukey-Hanning kernel and the Andrews automatic bandwidth routine. The estimation is performed using continuously updating weight iterations.

When working with a workfile that has a panel structure, you may use the panel equation estimation options. The command

eq.gmm(cx=fd, per=f) dj dj(-1) @ @dyn(dj)

estimates an Arellano-Bond “1-step” estimator with differencing of the dependent variable DJ, period fixed effects, and dynamic instruments constructed using DJ with observation specific lags from period

to 1.

To perform the “2-step” version of this estimator, you may use:

eq.gmm(cx=fd, per=f, gmm=perwhite, iter=oneb) dj dj(-1) @ @dyn(dj)

where the combination of the options “gmm=perwhite” and (the default) “iter=oneb” instructs EViews to estimate the model with the difference weights, to use the estimates to form period covariance GMM weights, and then re-estimate the model.

You may iterate the GMM weights to convergence using:

eq.gmm(cx=fd, per=f, gmm=perwhite, iter=seq) dj dj(-1) @ @dyn(dj)

Alternately:

eq.gmm(cx=od, gmm=perwhite, iter=oneb) dj dj(-1) x y @ @dyn(dj,-2,-6) x(-1) y(-1)

estimates an Arellano-Bond “2-step” equation using orthogonal deviations of the dependent variable, dynamic instruments constructed from DJ from period

, and ordinary instruments X(-1) and Y(-1).

Cross-references

See “Generalized Method of Moments” and “Panel Estimation” for discussion of the various GMM estimation techniques.

See also Equation::ardl.

predict

Equation Views

Prediction table for binary and ordered dependent variable models.

The prediction table displays the actual and estimated frequencies of each distinct value of the discrete dependent variable.

Syntax

eq_name.predict(n, options)

For binary models, you may optionally specify how large the estimated probability must be to be considered a success (

). Specify the cutoff level as the first option in parentheses after the keyword predict.

Options

n (default=.5)	Cutoff probability for success prediction in binary models (between 0 and 1).
prompt	Force the dialog to appear from within a program.
p	Print the prediction table.

Examples

equation eq1.binary(d=l) work c edu age race

eq1.predict(0.7)

Estimates a logit and displays the expectation-prediction table using a cutoff probability of 0.7.

Cross-references

See “Binary Dependent Variable Models” for a discussion of binary models, and “Expectation-Prediction (Classification) Table” for examples of prediction tables.

probit

Equation Methods

Estimation of binary dependent variable models with normal errors.

Equivalent to “binary(d=n)”.

See binary.

qrcrprocess

Equation Views

Displays a spool object producing a quantile process of the cointegrating relation.

Syntax

eq_name.qrcrprocess(options) [arg]

where arg is an optional list containing the quantile values (specified using numbers, scalar objects, or vectors) for which you wish to compute estimates.

• If arg is not specified, EViews will display results for the original equation along with coefficients for equations estimated at a set of equally spaced number of quantiles as specified by the “n=” option. If “n=” is not specified, the default is to display results for the deciles.

• If arg is specified, EViews will display results for the original equation along with coefficients for equations estimated at the specified quantiles.

Options

n=arg (default=10)	Number of quantiles for process estimates.
quantout=name	Save vector containing test quantile values.
coefout=name	Save matrix containing coefficient estimates of the cointegrating relation form. Each column of the matrix corresponds to a different quantile matching the corresponding quantile in "quantout=". To match the covariance matrix given in "covout=" you should take the @vec of the coefficient matrix.
prompt	Force the dialog to appear from within a program.
p	Print results.

Examples

ardl_eq.qrcrprocess

This generates a quantile process of the cointegrating relation for each quantile running from 0.1 to 0.9.

ardl_eq.qrcrprocess(n=4, quantout=_vec_q, coefout=_mat_cointrel)

ardl_eq.qrcrprocess(quantout=_vec_q, coefout=_mat_cointrel) 0.25 0.5 0.75

Both commands generate the cointegrating relation process for each of the quantile values 0.25, 0.5, and 0.75. Additionally, this produces 2 workfile objects, "_vec_q" (a vector), "_mat_cointrel¨(a matrix), and "_mat_cointrel" (a matrix), corresponding to the three quantile values and the cointegrating relation process.

Cross-references

See also Equation::qrecprocess and Equation::qrprocess.

qrecprocess

Equation Views

Displays a spool object producing a quantile process for each of the conditional error correction and error correction coefficients.

Syntax

eq_name.qrecprocess(options) [arg]

where arg is a optional list containing the quantile values (specified using numbers, scalar objects, or vectors) for which you wish to compute estimates.

• If arg is specified, EViews will display results for the original equation along with coefficients for equations estimated at the specified quantiles.

Options

n=arg (default=10)	Number of quantiles for process estimates.
quantout=name	Save vector containing test quantile values.
coefout=name	Saves two matrices differentiated by suffixes "_cec" and "_ec", corresponding to the coefficients associated with the CEC and EC forms, respectively. Each column of the matrix corresponds to a different quantile matching the corresponding quantile in "quantout=". To match the covariance matrix given in "covout=" you should take the @vec of the coefficient matrix.
covout=name	Saves two symmetric matrices, differentiated by suffixes "_cec" and "_ec", corresponding to the covariance matrices of coefficients associated with the CEC and EC forms, respectively.
prompt	Force the dialog to appear from within a program.
p	Print results.

Examples

ardl_eq.qrecprocess

This generates a quantile process of the CEC and EC coefficients for each quantile running from 0.1 to 0.9.

ardl_eq.qrecprocess(n=4, quantout=_vec_q, coefout=_mat_coefs, covout=_mat_covs)

ardl_eq.qrecprocess(quantout=_vec_q, coefout=_mat_coefs, covout=_mat_covs) 0.25 0.5 0.75

Both commands generate the process for CEC and EC coefficients for each of the quantile values 0.25, 0.5, and 0.75. Additionally, this produces 5 workfile objects, "_vec_q" (a vector), "_mat_coefs_cec" (a matrix), "_mat_coefs_ec" (a matrix), "_mat_covs_cec" (a matrix), and "_mat_covs_ec" (a matrix), corresponding to the three quantile values, coefficient process for each of the CEC and EC forms, covariances process for each of the CEC and EC forms, respectively.

Cross-references

See also Equation::qrcrprocess and Equation::qrprocess.

qreg	Equation Methods

Estimate a quantile regression specification.

Syntax

eq_name.qreg(options) y x1 [x2 x3 ...]

eq_name.qreg(options) linear_specification

Options

quant=number (default = 0.5)	Quantile to be fit (where number is a value between 0 and 1).
w=arg	Weight series or expression. Note: we recommend that, absent a good reason, you employ the default settings Inverse std. dev. weights (“wtype=istdev”) with EViews default scaling (“wscale=eviews”) for backward compatibility with versions prior to EViews 7.
wtype=arg (default=“istdev”)	Weight specification type: inverse standard deviation (“istdev”), inverse variance (“ivar”), standard deviation (“stdev”), variance (“var”).
wscale=arg	Weight scaling: EViews default (“eviews”), average (“avg”), none (“none”). The default setting depends upon the weight type: “eviews” if “wtype=istdev”, “avg” for all others.
cov=arg (default=“sandwich”)	Method for computing coefficient covariance matrix: “iid” (ordinary estimates), “sandwich” (Huber sandwich estimates), “boot” (bootstrap estimates). When “cov=iid” or “cov=sandwich”, EViews will use the sparsity nuisance parameter calculation specified in “spmethod=” when estimating the coefficient covariance matrix.
bwmethod=arg (default = “hs”)	Method for automatically selecting bandwidth value for use in estimation of sparsity and coefficient covariance matrix: “hs” (Hall-Sheather), “bf” (Bofinger), “c” (Chamberlain).
bw =number	Use user-specified bandwidth value in place of automatic method specified in “bwmethod=”.
bwsize=number (default = 0.05)	Size parameter for use in computation of bandwidth (used when “bw=hs” and “bw=bf”).
spmethod=arg (default=“kernel”)	Sparsity estimation method: “resid” (Siddiqui using residuals), “fitted” (Siddiqui using fitted quantiles at mean values of regressors), “kernel” (Kernel density using residuals) Note: “spmethod=resid” is not available when “cov=sandwich”.
btmethod=arg (default= “pair”)	Bootstrap method: “resid” (residual bootstrap), “pair” (xy-pair bootstrap), “mcmb” (MCMB bootstrap), “mcmba” (MCMB-A bootstrap).
btreps=integer (default=100)	Number of bootstrap repetitions
btseed=positive integer	Seed the bootstrap random number generator. If not specified, EViews will seed the bootstrap random number generator with a single integer draw from the default global random number generator.
btrnd=arg (default=“kn” or method previously set using rndseed).	Type of random number generator for the bootstrap: improved Knuth generator (“kn”), improved Mersenne Twister (“mt”), Knuth’s (1997) lagged Fibonacci generator used in EViews 4 (“kn4”) L’Ecuyer’s (1999) combined multiple recursive generator (“le”), Matsumoto and Nishimura’s (1998) Mersenne Twister used in EViews 4 (“mt4”).
btobs=integer	Number of observations for bootstrap subsampling (when “bsmethod=pair”). Should be significantly greater than the number of regressors and less than or equal to the number of observations used in estimation. EViews will automatically restrict values to the range from the number of regressors and the number of estimation observations. If omitted, the bootstrap will use the number of observations used in estimation.
btout=name	(optional) Matrix to hold results of bootstrap simulations.
k=arg (default=“e”)	Kernel function for sparsity and coefficient covariance matrix estimation (when “spmethod=kernel”): “e” (Epanechnikov), “r” (Triangular), “u” (Uniform), “n” (Normal–Gaussian), “b” (Biweight–Quartic), “t” (Triweight), “c” (Cosinus).
m=integer	Maximum number of iterations.
s	Use the current coefficient values in estimator coefficient vector as starting values (see also param).
s=number (default =0)	Determine starting values for equations. Specify a number between 0 and 1 representing the fraction of preliminary least squares coefficient estimates. Note that out of range values are set to the default.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
prompt	Force the dialog to appear from within a program.
p	Print estimation results.

Examples

equation eq1.qreg y c x

estimates the default least absolute deviations (median) regression for the dependent variable Y on a constant and X. The estimates use the Huber Sandwich method for computing the covariance matrix, with individual sparsity estimates obtained using kernel methods. The bandwidth uses the Hall and Sheather formula.

equation eq1.qreg(quant=0.6, cov=boot, btmethod=mcmba) y c x

estimates the quantile regression for the 0.6 quantile using MCMB-A bootstrapping to obtain estimates of the coefficient covariance matrix.

Cross-references

See “Quantile Regression” for a discussion of the quantile regression.

qrprocess

Equation Views

Display quantile process coefficient estimates (multiple quantile regression estimates).

Syntax

eq_name.qrprocess(options) [arg] [@coefs coeflist]

where arg is a optional list containing the quantile values (specified using numbers, scalar objects, or vectors) for which you wish to compute estimates, and optionally the @coefs keyword followed by a coeflist of the subset of coefficients to display.

• If arg is specified, EViews will display results for the original equation along with coefficients for equations estimated at the specified quantiles.

• If a coeflist is not provided, results for all coefficients will be displayed. For models that contain an intercept, the coeflist may consist of the @incptonly keyword, indicating that only results for the intercept will be displayed.

You may specify a maximum of 1000 total coefficients (number of display coefficients times the number of quantiles) and a maximum of 500 quantiles.

All estimation will be performed using the settings from the original equation.

Options

n=arg (default=10)	Number of quantiles for process estimates.
graph	Display process estimate results as graph.
size=arg (default=0.95)	Confidence interval size for graph display
quantout=name	Save vector containing test quantile values.
coefout=name	Save matrix containing test coefficient estimates. Each column of the matrix corresponds to a different quantile matching the corresponding quantile in “quantout=”. To match the covariance matrix given in “covout=” you should take the @vec of the coefficient matrix.
covout=name	Save symmetric matrix containing covariance matrix for the vector set of coefficient estimates.
prompt	Force the dialog to appear from within a program.
p	Print output.

Examples

equation eq1.qreg log(y) c log(x)

eq1.qrprocess

estimates a quantile (median) regression of LOG(Y) on a constant and LOG(X), and displays results for all nine quantiles in a table

Similarly,

equation eq1.qreg(quant=.4) log(y) c log(x)

eq1.qrprocess(coefcout=cout)

displays the coefficient estimated at the deciles (and at 0.4), and saves the coefficient matrix to COUT.

eq1.qrprocess(coefout=cout, n=4, graph)

eq1.qrprocess(coefout=cout, graph) .25 .5 .75

both estimate coefficients for the three quartiles and display the results in a graph, as does the equivalent:

vector v1(3)

v1.fill .25 .5 .75

eq1.qrprocess(graph) v1

Cross-references

See “Process Coefficients” for a discussion of the quantile process.

See also Equation::qrcrprocess and Equation::qrecprocess.

qrslope

Equation Views

Perform Wald test of equality of slope coefficients across multiple quantile regression estimates. The equality test restrictions are of the form:

for the slope coefficients

Syntax

eq_name.qrslope(options) [arg] [@coefs coeflist]

• If arg is not specified, EViews will perform tests for the existing equation and coefficients for equations estimated at a set of equally spaced quantiles as specified by the “n=” option. If “n=” is not specified, the default is to display results for the quartiles (.25, .75).

• If arg is specified, EViews will perform results for the original equation along with tests including coefficients for equations estimated at the specified quantiles.

• If a coeflist is not provided, all of the slope coefficients will be employed in the test.

You may specify a maximum of 1000 total coefficients (number of coefficients in the equation specification times the number of quantiles) and a maximum of 500 quantiles in the test.

All estimation will be performed using the settings from the original equation.

Options

n=arg (default=4)	Number of quantiles for process estimates.
quantout=name	Save vector containing test quantile values.
coefout=name	Save matrix containing test coefficient estimates. Each column of the matrix corresponds to a different quantile matching the corresponding quantile in “quantout=”. To match the covariance matrix given in “covout=” you should take the @vec of the coefficient matrix.
covout=name	Save symmetric matrix containing covariance matrix for the vector set of coefficient estimates.
prompt	Force the dialog to appear from within a program.
p	Print output from the test.

Examples

equation eq1.qreg log(y) c log(x)

eq1.qrslope

estimates a quantile (median) regression of LOG(Y) on a constant and LOG(X), and tests for the equality of the coefficients of LOG(X) for all three of the quartiles.

Similarly,

equation eq1.qreg(quant=.4) log(y) c log(x)

eq1.qrslope(coefcout=cout)

tests for equality of the LOG(X) coefficient estimated at {.25, .4, .5, .75}, and saves the coefficient matrix to COUT. Both

eq1.qrslope(coefout=count, n=10)

eq1.qrslope(coefout=cout) .1 .2 .3 .4 .5 .6 .7 .8 .9

perform the Wald test for equality of the slope coefficient across all of the deciles, as does the equivalent

vector v1(9)

v1.fill .1,.2,.3,.4,.5,.6,.7,.8,.9

eq1.qrslope v1

Cross-references

See “Slope Equality Test” for a discussion of the slope equality test.

See also Equation::ardl.

srcoefs

Equation Views

Displays a spool object with the results of error-correction regressions for each cross-section in PMG estimation.

Syntax

eq_name.srcoefs

Options

p	Print results.

Example

equation eq.ardl log(cons) log(inf)

eq.srcoefs

Displays a spool object with the results of error-correction regressions for each cross-section in PMG estimation.

Cross-references

See “Pooled Mean Group ARDL Estimation” and “ARDL and Quantile ARDL”for discussion.

See also Equation::ardl.

strconstant

Equation Views

Compute tests of parameter constancy of the base specification against a smooth transition alternative in a smooth threshold regression.

Syntax

eq_name.strconstant(options)

Options

p	Print output from the test.

Cross-references

See “Smooth Transition Regression” for discussion.

See also Equation::strlinear and Equation::strnonlin.

strlinear

Equation Views

Compute tests for linearity of the base specification against the smooth threshold alternative in a smooth threshold regression.

Syntax

eq_name.strlinear(options)

Options

p	Print output from the test.

Cross-references

See “Smooth Transition Regression” and “Linearity Testing” for discussion.

See also Equation::strlinear and Equation::strnonlin.

strnonlin

Equation Views

Compute tests for additional nonlinearity against additive or encapsulated alternatives (for equations in a smooth threshold regression).

Syntax

eq_name.strnonlin(options)

Options

encap	Compute tests for additional nonlinearity against encapsulated alternatives.
p	Print output from the test.

Cross-references

See “Smooth Transition Regression” and “Remaining Nonlinearity Tests” for discussion.

See also Equation::strconstant and Equation::strlinear.

strwgts

Equation Views

Compute and display the transition weights in a smooth threshold regression.

The default display shows a graph of the transition function. You may also display the weights for each observation in the estimation sample.

Syntax

eq_name.strwgts(options)

Options

view=arg	Weight display: “graph” (graph of the weight for each individual in the estimation sample), “sheet” (spreadsheet containing weights for each individual), “summary” (summary statistics). The default view displays a graph of the function with optional borders.
ab=arg	Additional graph borders to display when showing the default view of the weights: “none” (do not display borders)”, “boxplot” (display boxplot borders), “histogram” (display a histogram). The default view shows a boxplot on each border.
output=arg	Optional name of matrix to save the data used in the function plot.
prompt	Force the dialog to appear from within a program.
p	Print output from the test.

Cross-references

See “Smooth Transition Regression” and “Remaining Nonlinearity Tests” for discussion.

See also Equation::ardl.

testadd

Equation Views

Test whether to add regressors to an estimated equation.

Tests the hypothesis that the listed variables were incorrectly omitted from an estimated equation (only available for equations estimated by list). The test displays some combination of Wald and LR test statistics, as well as the auxiliary regression.

Syntax

eq_name.testadd(options) arg1 [arg2 arg3 ...]

eq_name.testadd(options) arg1 [arg2 arg3 ...] [@nv x1 x2 x3 ...]

List the names of the series or groups of series to test for omission after the keyword.

For equations estimated using breakls, there are two types of added series, those with coefficients that break, and those with coefficients that are non-breaking. The former should be listed before, and the latter should be listed after the optional @nv keyword.

Options

prompt	Force the dialog to appear from within a program.
p	Print output from the test.

Examples

equation oldeq.ls sales c adver lsales ar(1)

oldeq.testadd gdp gdp(-1)

tests whether GDP and GDP(-1) belong in the specification for SALES using the equation OLDEQ.

Cross-references

See “Coefficient Diagnostics” for further discussion.

See also Equation::testdrop and Equation::wald.

testdrop

Equation Views

Test whether to drop regressors from a regression.

Tests the hypothesis that the listed variables were incorrectly included in the estimated equation (only available for equations estimated by list). The test displays some combination of

and LR test statistics, as well as the test regression.

Syntax

eq_name.testdrop(options) arg1 [arg2 arg3 ...]

List the names of the series or groups of series to test for omission after the keyword.

Options

prompt	Force the dialog to appear from within a program.
p	Print output from the test.

Examples

equation oldeq.ls sales c adver lsales ar(1)

oldeq.testdrop adver

tests whether ADVER should be excluded from the specification for SALES using a the equation OLDEQ.

Cross-references

See “Coefficient Diagnostics” for further discussion of testing coefficients.

See also Equation::testadd and Equation::wald.

testfit

Equation Views

Carry out the Hosmer-Lemeshow and/or Andrews goodness-of-fit tests for estimated binary models.

Syntax

binary_equation.testfit(options)

Options

h	Group by the predicted values of the estimated equation.
s=series_name	Group by the specified series.
integer (default=10)	Specify the number of quantile groups in which to classify observations.
u	Unbalanced grouping. Default is to randomize ties to balance the number of observations in each group.
v	Group according to the values of the reference series.
l=integer (default=100)	Limit the number of values to use for grouping. Should be used with the “v” option.
prompt	Force the dialog to appear from within a program.
p	Print the result of the test.

Examples

equation eq1.binary work c age edu

eq1.testfit(h,5,u)

estimates a probit specification, and tests goodness-of-fit by comparing five unbalanced groups of actual data to those estimated by the model.

Cross-references

See “Goodness-of-Fit Tests” for a discussion of the Andrews and Hosmer-Lemeshow tests.

threshold

Equation Methods

Estimation by discrete or smooth threshold least squares, including threshold autoregression.

Syntax

eq_name.threshold(options) y z1 [z2 z3 ...] [@nv x1 x2 x3 ...] @thresh t1 [t2 t3 ...]

List the dependent variable first, followed by a list of the independent variables that have coefficients that are allowed to vary across threshold, followed optionally by the keyword @nv and a list of non-varying coefficient variables.

List a threshold variable or variables (for model selection) or a single integer or range pairs after the keyword @thresh. The integer or range pairs indicate a self-exciting model with the lagged dependent variable as the threshold variable.

For smooth threshold equations you may specify variables that are to be included only in the base specification or only in the alternative specification. Base-only variables should be specified in parentheses using the @base key, as in “@base(x1) @base(x2) @base(x3 x4)”. Alternative-only variables may be specified analogously using the @alt key.

Options

Specification Options

type=arg (default=“discrete”)

Type of threshold estimation: “discrete” (discrete), “smooth” (smooth).

Discrete Threshold Options

method=arg (default=“seqplus1”)	Threshold selection method: “seqplus1” (sequential tests of single versus thresholds), “seqall” (sequential test of all possible versus thresholds), “glob” (tests of global vs. no thresholds), “globplus1” (tests of versus globally determined thresholds), “globinfo” (information criteria evaluation)., “fixedseq” (fixed number of sequentially determined thresholds), “fixedglob” (fixed number of globally determined thresholds), “user” (user-specified thresholds)
nthresh=arg (default=1)	Number of thresholds for fixed number threshold selection methods.
select=arg	Sub-method setting (options depend on “method=”). (1) if “method=glob”: Sequential ("seq") (default), Highest significant ("high"), ("udmax"), ("wdmax"). (2) if “method=globinfo”: Schwarz criterion (“bic” or “sic”) (default), Liu-Wu-Zidek criterion (“lwz”).
trim=arg (default=5)	Trimming percentage for determining minimum segment size (5, 10, 15, 20, 25).
maxthresh=integer (default=5)	Maximum number of thresholds to allow (not applicable if “method=seqall”).
maxlevels=integer (default=5)	Maximum number of threshold levels to consider in sequential testing (applicable when “method=sequall”).
size=arg (default=5)	Test sizes for use in sequential determination and final test evaluation (10, 5, 2.5, 1) corresponding to 0.10, 0.05, 0.025, 0.01, respectively
heterr	Assume regimes specific error distributions in variance computation.
commondata	Assume a common distribution for the data across segments (only applicable if original equation is estimated with a robust covariance method, “heterr” is not specified).

Smooth Threshold Options

smoothtrans=arg (default=“logistic”)	Smooth threshold transition function: “logistic” (logistic), “logistic2” (second-order logistic), “exponential” (exponential), “normal” (normal).
smoothstart=arg (default=“grid_conc”)	Smoth threshold starting value method: or fixed number threshold selection methods: “grid_conc” (grid search with concentrated regression coefficients”, “grid_zeros” (grid search with zero regression coefficients), “data” (data-based), “user” (user-specified using the contents of the coefficient vector in the workfile).
smoothst=arg	Sub-method setting (options depend on “method=”). (1) if “method=glob”: Sequential ("seq") (default), Highest significant ("high"), ("udmax"), ("wdmax"). (2) if “method=globinfo”: Schwarz criterion (“bic” or “sic”) (default), Liu-Wu-Zidek criterion (“lwz”).

General Options

w=arg	Weight series or expression.
wtype=arg (default=“istdev”)	Weight specification type: inverse standard deviation (“istdev”), inverse variance (“ivar”), standard deviation (“stdev”), variance (“var”).
wscale=arg	Weight scaling: EViews default (“eviews”), average (“avg”), none (“none”). The default setting depends upon the weight type: “eviews” if “wtype=istdev”, “avg” for all others.
cov=keyword	Covariance type (optional): “white” (White diagonal matrix), “hac” (Newey-West HAC).
nodf	Do not perform degree of freedom corrections in computing coefficient covariance matrix. The default is to use degree of freedom corrections.
covlag=arg (default=1)	Whitening lag specification: integer (user-specified lag value), “a” (automatic selection).
covinfosel=arg (default=“aic”)	Information criterion for automatic selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn) (if “lag=a”).
covmaxlag=integer	Maximum lag-length for automatic selection (optional) (if “lag=a”). The default is an observation-based maximum of .
covkern=arg (default=“bart”)	Kernel shape: “none” (no kernel), “bart” (Bartlett, default), “bohman” (Bohman), “daniell” (Daniel), “parzen” (Parzen), “parzriesz” (Parzen-Riesz), “parzgeo” (Parzen-Geometric), “parzcauchy” (Parzen-Cauchy), “quadspec” (Quadratic Spectral), “trunc” (Truncated), “thamm” (Tukey-Hamming), “thann” (Tukey-Hanning), “tparz” (Tukey-Parzen).
covbw=arg (default=“fixednw”)	Kernel Bandwidth: “fixednw” (Newey-West fixed), “andrews” (Andrews automatic), “neweywest” (Newey-West automatic), number (User-specified bandwidth).
covnwlag=integer	Newey-West lag-selection parameter for use in nonparametric kernel bandwidth selection (if “covbw=neweywest”).
covbwint	Use integer portion of bandwidth.
prompt	Force the dialog to appear from within a program.
p	Print basic estimation results.

Examples

equation eq1.threshold(method=fixedseq, type=discrete) ss_transf c ss_transf(-1 to -11) @thresh 2

uses the fixed number of thresholds test to determine the optimal threshold in a model regressing SS_TRANSF on the threshold variables C and SS_TRANSF(-1 to -11).

equation eq2.threshold(method=fixedseq, type=discrete) ss_transf c ss_transf(-1 to -11) @thresh 1 5

uses the fixed number of thresholds test to determine the optimal threshold and does model selection over lags of SS_TRANSF from SS_TRANSF(-1) to SS_TRANSF(-5).

equation eq3.threshold(method=user, threshold=7.44) ss_transf c @nv ss_transf(-1 to -11) @thresh 2

estimates the model with one user-specified threshold value. In addition, the variables SS_TRANSF(-1 to -11) are restricted to have common coefficients across the regimes.

Cross-references

See “Discrete Threshold Regression” and “Smooth Transition Regression” for a discussion of the various forms of threshold models.

transprobs

Equation Views

Display regime transition probabilities and expected durations for a switching regression equation.

Syntax

equation_name.transprobs(options)

where equation_name is the name of an equation estimated using switching regression.

Options

type=arg (default=“summary”)	Transition probability results to display: summary (“default”), transition probabilities (“trans”), expected durations (“expect”). The default summary displays the transition matrix and expected regime durations for constant transition probability models, and descriptive statistics for the transition and expected durations for varying probability models.
view=arg (default=“graph”)	Display method: graph (“graph”), spreadsheet (“sheet”), table (“table”). Applicable when displaying the transition probabilities or expected durations (“type=trans” or “type=expect”). The spreadsheet form represents shows the transition probabilities or regime expected durations in columns and observations in rows. The table form displays the transition probabilities or expected durations in a table (in a single matrix for a time-constant model, and individual matrices for a time-varying model).
prompt	Force the dialog to appear from within a program.
p	Print results.

Examples

equation eq1.switchreg(type=markov) y c @nv ar(1) ar(2) ar(3)

eq1.transprobs

displays the default summary of the transition probabilities estimated in EQ1.

The command

eq1.transprobs(type=trans)

displays the transition probabilities in a graph, while

eq1.transprobs(type=trans, view=sheet)

displays the transition probabilities in a spreadsheet, with each row column representing one of the probabilities and each row representing an observation.

eq1.transprobs(type=trans, view=table)

displays the transition probabilities in a table.

eq1.transprobs(type=expect, view=sheet)

displays the expected durations in spreadsheet form.

Cross-references

See “Switching Regression” for discussion.

lag=arg (default=“a”)	Method of selecting the lag length (number of first difference terms) to be included in the regression: “a” (automatic information criterion based selection), or integer (user-specified lag length).
lagtype=arg (default=“sic”)	Information criterion or method to use when computing automatic lag length selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn), “msaic” (Modified Akaike), “msic” (Modified Schwarz), “mhqc” (Modified Hannan-Quinn), “tstat” (t-statistic).
maxlag=integer	Maximum lag length to consider when performing automatic lag-length selection default= where is the number of coefficients in the cointegrating equation. Applicable when “lag=a”.
lagpval=number (default=0.10)	Probability threshold to use when performing automatic lag-length selection using a t-test criterion. Applicable when both “lag=a” and “lagtype=tstat”.
nodf	Do not degree-of-freedom correct estimates of the variances.
p	Print results.

method=arg (default=“fmols”)	Estimation method: Fully Modified OLS (“fmols”), Canonical Cointegrating Regression (“ccr”), Dynamic OLS (“dols”) Note that CCR estimation is not available in panel settings.
trend=arg (default=“const”)	Specification for the powers of trend to include in the cointegrating and regressor equations: None (“none”), Constant (“const”), Linear trend (“linear”), Quadratic trend (“quadratic”). Note that the specification implies all trends up to the specified order so that choosing a quadratic trend instructs EViews to include a constant and a linear trend term along with the quadratic.
regtrend=arg (default=“none”)	Additional trends to include in the regressor equations (but not the cointegrating equation): None (“none”), Constant (“const”), Linear trend (“linear”), Quadratic trend (“quadratic”). Only trend orders higher than those specified by “trend=” will be considered. Note that the specification implies all trends up to the specified order so that choosing a quadratic trend instructs EViews to include a constant and a linear trend term along with the quadratic.
regdiff	Estimate the regressor equation innovations directly using the difference specifications.
coef=arg	Specify the name of the coefficient vector; the default behavior is to use the “C” coefficient vector.
btwcoefs=arg	Save the cross-section specific deterministic coefficient estimates in a matrix object (one row per cross-section).
btwcovs=arg	Save the covariances of the cross-section specific deterministic coefficient estimates in a matrix object (one row per cross-section, with each row holding the vech of the covariance).
prompt	Force the dialog to appear from within a program.
p	Print results.

panmethod=arg (default=“pooled”)	Panel estimation method: pooled (“pooled”), pooled weighted (“weighted”), grouped (“grouped”)
pancov=sandwich	Estimate the coefficient covariance using a sandwich method that allows for cross-section heterogeneity.

lltype=arg (default=“fixed”)	Lag-lead method: fixed values (“fixed”), automatic selection - Akaike (“aic”), automatic - Schwarz (“sic”), automatic - Hannan-Quinn (“hqc”), None (“none”).
lag=arg	Lag specification: integer (required user-specified number of lags if “lltype=fixed”).
lead=arg	Lead specification: integer (required user-specified number of lags if “lltype=fixed”).
maxll=integer	Maximum lag and lead-length for automatic selection (optional user-specified integer if “lltype=” is used to specify automatic selection). The default is an observation-based maximum.
cov=arg	Coefficient covariance method: (default) long-run variance scaled OLS, unscaled OLS (“ols”), White (“white”), Newey-West (“hac”).
nodf	Do not degree-of-freedom correct the coefficient covariance estimate.

panwgtlag=arg (default=0)	Lag specification: integer (user-specified lag value), “a” (automatic selection).
panwgtinfosel=arg (default=“aic”)	Information criterion for automatic selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn) (if “lrvarlag=a”).
panwgtmaxlag=integer	Maximum lag-length for automatic selection (optional) (if “lrvarlag=a”). The default is an observation-based maximum.
panwgtkern=arg (default=“bart”)	Kernel shape: “none” (no kernel), “bart” (Bartlett, default), “bohman” (Bohman), “daniell” (Daniell), “parzen” (Parzen), “parzriesz” (Parzen-Riesz), “parzgeo” (Parzen-Geometric), “parzcauchy” (Parzen-Cauchy), “quadspec” (Quadratic Spectral), “trunc” (Truncated), “thamm” (Tukey-Hamming), “thann” (Tukey-Hanning), “tparz” (Tukey-Parzen).
panwgtbw=arg (default=“nwfixed”)	Bandwidth:: “fixednw” (Newey-West fixed), “andrews” (Andrews automatic), “neweywest” (Newey-West automatic), number (User-specified bandwidth).
panwgtnwlag=integer	Newey-West lag-selection parameter for use in nonparametric bandwidth selection (if “bw=neweywest”).
panwgtbwoffset=integer (default=0)	Apply offset to automatically selected bandwidth. For settings where “cov=hac”, “covkern=” is specified, and “covbw=” is not user-specified.
panwgtbwint	Use integer portion of bandwidth chosen by automatic selection method (“bw=andrews” or “bw=neweywest”).

l=number (default=0)	Set value for the left censoring limit.
r=number (default=none)	Set value for the right censoring limit.
l=series_name, i	Set series name of the indicator variable for the left censoring limit.
r=series_name, i	Set series name of the indicator variable for the right censoring limit.
t	Estimate truncated model.
d=arg (default=“n”)	Specify error distribution: normal (“n”), logistic (“l”), Type I extreme value (“x”).
optmethod = arg	Optimization method: “bfgs” (BFGS); “newton” (Newton-Raphson), “opg” or “bhhh” (OPG or BHHH), “legacy” (EViews legacy). Newton-Raphson is the default method.
optstep = arg	Step method: “marquardt” (Marquardt); “dogleg” (Dogleg); “linesearch” (Line search). Marquardt is the default method.
cov=arg	Covariance method: “ordinary” (default method based on inverse of the estimated information matrix), “huber” or “white” (Huber-White sandwich methods)., “cr” (cluster robust).
covinfo = arg	Information matrix method: “opg” (OPG); “hessian” (observed Hessian - default). (Applicable when non-legacy “optmethod=”).
df	Degree-of-freedom correct the coefficient covariance estimate.(For non-cluster robust methods estimated using non-legacy estimation).
h	Huber-White quasi-maximum likelihood (QML) standard errors and covariances. (Legacy option applicable when “optmethod=legacy”).
crtype=arg (default “cr1”)	Cluster robust weighting method: “cr0” (no finite sample correction), “cr1” (finite sample correction), when “cov=cr”.
crname=arg	Cluster robust series name, when “cov=cr”.
m=integer	Set maximum number of iterations.
c=scalar	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled coefficients. The criterion will be set to the nearest value between 1e-24 and 0.2.
s	Use the current coefficient values in “C” as starting values (see also param).
s=number	Specify a number between zero and one to determine starting values as a fraction of EViews default values (out of range values are set to “s=1”).
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
prompt	Force the dialog to appear from within a program.
p	Print results.

f	Chow forecast test. For this option, you must specify a single breakpoint to test (default performs breakpoint test).
p	Print the result of test.

prompt	Force the dialog to appear from within a program.
nopair	Display the intervals concentrically. The default is to display them in pairs for each probability value

lag=arg (default=0)	Lag specification: integer (user-specified lag value), “a” (automatic selection).
infosel=arg (default=“aic”)	Information criterion for automatic selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn) (if “lag=a”).
maxlag=integer	Maximum lag-length for automatic selection (optional) (if “lag=a”). The default is an observation-based maximum.

kern=arg (default=“bart”)	Kernel shape: “none” (no kernel), “bart” (Bartlett, default), “bohman” (Bohman), “daniell” (Daniel), “parzen” (Parzen), “parzriesz” (Parzen-Riesz), “parzgeo” (Parzen-Geometric), “parzcauchy” (Parzen-Cauchy), “quadspec” (Quadratic Spectral), “trunc” (Truncated), “thamm” (Tukey-Hamming), “thann” (Tukey-Hanning), “tparz” (Tukey-Parzen).
bw=arg (default=“nwfixed”)	Bandwidth: “fixednw” (Newey-West fixed), “andrews” (Andrews automatic), “neweywest” (Newey-West automatic), number (User-specified bandwidth).
nwlag=integer	Newey-West lag-selection parameter for use in nonparametric bandwidth selection (if “bw=neweywest”).
bwoffset=integer (default=0)	Apply integer offset to bandwidth chosen by automatic selection method (“bw=andrews” or “bw=neweywest”).
bwint	Use integer portion of bandwidth chosen by automatic selection method (“bw=andrews” or “bw=neweywest”).

covlag=arg (default=0)	Lag specification: integer (user-specified lag value), “a” (automatic selection).
covinfosel=arg (default=“aic”)	Information criterion for automatic selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn) (if “lag=a”).
covmaxlag=integer	Maximum lag-length for automatic selection (optional) (if “lag=a”). The default is an observation-based maximum.

covkern=arg (default=“bart”)	Kernel shape: “none” (no kernel), “bart” (Bartlett, default), “bohman” (Bohman), “daniell” (Daniel), “parzen” (Parzen), “parzriesz” (Parzen-Riesz), “parzgeo” (Parzen-Geometric), “parzcauchy” (Parzen-Cauchy), “quadspec” (Quadratic Spectral), “trunc” (Truncated), “thamm” (Tukey-Hamming), “thann” (Tukey-Hanning), “tparz” (Tukey-Parzen).
covbw=arg (default=“nwfixed”)	Bandwidth: “fixednw” (Newey-West fixed), “andrews” (Andrews automatic), “neweywest” (Newey-West automatic), number (User-specified bandwidth).
covnwlag=integer	Newey-West lag-selection parameter for use in nonparametric bandwidth selection (if “covbw=neweywest”).
covbwoffset=integer (default=0)	Apply integer offset to bandwidth chosen by automatic selection method (“bw=andrews” or “bw=neweywest”).
covbwint	Use integer portion of bandwidth chosen by automatic selection method (“bw=andrews” or “bw=neweywest”).

lrvar=ordinary	Compute DOLS estimates of the long-run residual variance used in covariance calculation using the ordinary variance.
lrvarlag=arg (default=0)	For DOLS estimates of the long-run residual variance used in covariance calculation, lag specification: integer (user-specified lag value), “a” (automatic selection).
lrvarinfosel=arg (default=“aic”)	For DOLS estimates of the long-run residual variance used in covariance calculation, information criterion for automatic selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn) (if “lrvarlag=a”).
lrvarmaxlag=integer	For DOLS estimates of the long-run residual variance used in covariance calculation, maximum lag-length for automatic selection (optional) (if “lrvarlag=a”). The default is an observation-based maximum.
lrvarkern=arg (default=“bart”)	For DOLS estimates of the long-run residual variance used in covariance calculation, Kernel shape: “none” (no kernel), “bart” (Bartlett, default), “bohman” (Bohman), “daniell” (Daniell), “parzen” (Parzen), “parzriesz” (Parzen-Riesz), “parzgeo” (Parzen-Geometric), “parzcauchy” (Parzen-Cauchy), “quadspec” (Quadratic Spectral), “trunc” (Truncated), “thamm” (Tukey-Hamming), “thann” (Tukey-Hanning), “tparz” (Tukey-Parzen).
lrvarbw=arg (default=“nwfixed”)	For DOLS estimates of the long-run residual variance used in covariance calculation, bandwidth:: “fixednw” (Newey-West fixed), “andrews” (Andrews automatic), “neweywest” (Newey-West automatic), number (User-specified bandwidth).
lrvarnwlag=integer	For DOLS estimates of the long-run residual variance used in covariance calculation, Newey-West lag-selection parameter for use in nonparametric bandwidth selection (if “bw=neweywest”).
lrvarbwoffset=integer (default=0)	For DOLS estimates of the long-run residual variance used in covariance calculation, apply offset to automatically selected bandwidth. For settings where “cov=hac”, “covkern=” is specified, and “covbw=” is not user-specified.
lrvarbwint	For DOLS estimates of the long-run residual variance used in covariance calculation, use integer portion of bandwidth.

d=arg (default=“p”)	Likelihood specification: Poisson likelihood (“p”), normal quasi-likelihood (“n”), exponential likelihood (“e”), negative binomial likelihood or quasi-likelihood (“b”).
v=positive_num (default=1)	Specify fixed value for QML parameter in normal and negative binomial quasi-likelihoods.
optmethod = arg	Optimization method: “bfgs” (BFGS); “newton” (Newton-Raphson), “opg” or “bhhh” (OPG or BHHH), “legacy” (EViews legacy). Newton-Raphson is the default method.
optstep = arg	Step method: “marquardt” (Marquardt); “dogleg” (Dogleg); “linesearch” (Line search). Marquardt is the default method.
cov=arg	Covariance method: “ordinary” (default method based on inverse of the estimated information matrix), “huber” or “white” (Huber-White sandwich methods)., “glm” (GLM method),““cr” (cluster robust).
covinfo = arg	Information matrix method: “opg” (OPG); “hessian” (observed Hessian). (Applicable when non-legacy “optmethod=”.)
df	Degree-of-freedom correct the coefficient covariance estimate.(For non-cluster robust methods estimated using non-legacy estimation).
h	Huber-White quasi-maximum likelihood (QML) standard errors and covariances. (Legacy option Applicable when “optmethod=legacy”).
g	GLM standard errors and covariances. (Legacy option Applicable when “optmethod=legacy”).
crtype=arg (default “cr1”)	Cluster robust weighting method: “cr0” (no finite sample correction), “cr1” (finite sample correction), when “cov=cr”.
crname=arg	Cluster robust series name, when “cov=cr”.
m=integer	Set maximum number of iterations.
c=scalar	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled coefficients. The criterion will be set to the nearest value between 1e-24 and 0.2.
s	Use the current coefficient values in “C” as starting values (see also param).
s=number	Specify a number between zero and one to determine starting values as a fraction of the EViews default values (out of range values are set to “s=1”).
prompt	Force the dialog to appear from within a program.
p	Print the result.

t	Display spreadsheet view of the values of the derivatives with respect to the coefficients evaluated at each observation.
g	Display multiple graphs showing the derivatives of the equation specification with respect to the coefficients, evaluated at each observation.
p	Print results.

notyet	Use observations where an individual is not yet treated as the comparison group. Default is to only use individuals that are never treated as the comparison.
both	Use both observations where an individual is never treated or has not yet been treated as the comparison group. Default is to only use individuals that are never treated as the comparison.
p	Print output.

noci	Do not generate confidence intervals for asymmetric regressors. Note that confidence intervals can only be generated for asymmetric regressors.
noshade	Display confidence interval using lines instead of shaded bands.
level=number (default = 0.95)	Number between 0 and 1 representing the confidence interval level.
reps=integer (default = 999)	Number of Monte Carlo repetitions used in the generation of confidence intervals (if applicable).
f=number	Fraction of failed repetitions before stopping. Only applicable if a se_pattern is provided.
prompt	Force the dialog to appear from within a program.
p	Print output.

t	Display spreadsheet view of the values of the gradients of the objective function with respect to the coefficients evaluated at each observation.
g	Display multiple graph showing the gradients of the objective function with respect to the coefficients evaluated at each observation.
p	Print results.

2step	Use the Heckman 2-step estimation method. Note that this option is incompatible with the maximum likelihood options below.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
prompt	Force the dialog to appear from within a program.
p	Print the estimation results.

type = keyword	where keyword is either “BPG” (Breusch-Pagan-Godfrey - default), “Harvey”, “Glejser”, “ARCH”, or “White”.
c	include cross terms for White test.
lags = int	set number of lags to use for ARCH test. (Only applies when type = “ARCH”.
prompt	Force the dialog to appear from within a program.

@regs	include every regressor from the original equation.
@grads	include every gradient in the original equation (non-linear equations only).
@grad(int)	include the int-th gradient.
@white(key)	include white-style regressors (the cross-product of the regressor list, or the gradient list if non-linear). key may be on of the following keywords: “@regs” (include every regressor from the original equation), “@drop(variables)” (drop a variable from those already included. For example, “@white(@regs @drop(x2))” would include all original regressors apart from X2), “@comp” (include the compatible style White regressors, i.e. levels, squares, and cross-products).
@arch(lag_structure)	include an ARCH specification with the number of lags specified by lag_structure. If lag_structure is a single number, then it defines the number of lags to include. Otherwise, the lag structure is in pairs. For example, “@arch(1 5 9 10)” will include lags 1, 2, 3, 4, 5, 9, 10.
@uw(variables)	include unweighted variables (only applicable in a weighted original equation).

t	Show a table of the statistics (the default is to display a graph view of the specified statistics).
rows = key	The number of observations/rows to display in the table, where key can be either “50”, “100” (default), “150”, or “200”.
g=arg	arg is the name of an object in which the graph output will be saved.
prompt	Force the dialog to appear from within a program.

rstudent	The studentized residual: the t-statistic on a dummy variable that is equal to 1 on that observation only.
dffits	The scaled difference in fitted values.
drresid	Dropped residual: the estimated residual for that observation had the equation been run without that observation.
covratio	The ratio of the covariance matrix of the coefficients with and without that observation.
hatmatrix	Diagonal elements of the hat matrix:

c	Clears all text fields in the label.
d	Sets the description field to text.
s	Sets the source field to text.
u	Sets the units field to text.
r	Appends text to the remarks field as an additional line.
p	Print the label view.

noconst	Do not include a constant in the instrumental list. Without this option, a constant will always be included as an instrument, even if not specified explicitly.
w=arg	Weight series or expression.
wtype=arg (default=“istdev”)	Weight specification type: inverse standard deviation (“istdev”), inverse variance (“ivar”), standard deviation (“stdev”), variance (“var”).
wscale=arg	Weight scaling: EViews default (“eviews”), average (“avg”), none (“none”). The default setting depends upon the weight type: “eviews” if “wtype=istdev”, “avg” for all others.
kclass=number	Set the value of in the K‑class estimator. If omitted, LIML is performed, and is calculated as part of the estimation procedure.
se = arg (default=“iv”)	Set the standard-error calculation type: IV based (“se=iv”), K-Class based (“se=kclass”), Bekker (“se=bekk”), or Hansen, Hausman, and Newey (“se=hhn”).
m=integer	Set maximum number of iterations.
c=number	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled coefficients. The criterion will be set to the nearest value between 1e-24 and 0.2.
numericderiv / ‑numericderiv	[Do / do not] use numeric derivatives only. If omitted, EViews will follow the global default.
fastderiv / ‑fastderiv	[Do / do not] use fast derivative computation. If omitted, EViews will follow the global default. Available only for legacy estimation (“optmeth=legacy”).
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
prompt	Force the dialog to appear from within a program.
p	Print estimation results.

indicator	Include indicator saturation detection as part of estimation routine.
w=arg	Weight series or expression. Note: we recommend that, absent a good reason, you employ the default settings Inverse std. dev. weights (“wtype=istdev”) with EViews default scaling (“wscale=eviews”) for backward compatibility with versions prior to EViews 7.
wtype=arg (default=“istdev”)	Weight specification type: inverse standard deviation (“istdev”), inverse variance (“ivar”), standard deviation (“stdev”), variance (“var”).
wscale=arg	Weight scaling: EViews default (“eviews”), average (“avg”), none (“none”). The default setting depends upon the weight type: “eviews” if “wtype=istdev”, “avg” for all others.
z	Turn off backcasting in ARMA models where “arma=cls”.
optmethod = arg	Optimization method for nonlinear least squares and ARMA: “bfgs” (BFGS); “newton” (Newton-Raphson), “opg” or “bhhh” (OPG or BHHH), “kohn” (Kohn-Ansley for ARMA estimated by ML or GLS), or “legacy” (EViews legacy for nonlinear least squares and ARMA estimated by CLS). Gauss-Newton is the default method.
optstep = arg	Step method for nonlinear least squares and ARMA: “marquardt” (Marquardt); “dogleg” (Dogleg); “linesearch” (Line search). Marquardt is the default method.
cov=arg	Covariance method: “ordinary” (default method based on inverse of the estimated information matrix), “huber” or “white” (Huber-White sandwich method available for nonlinear least squares or ARMA estimated by CLS), “hac” (Newey-West HAC, available for nonlinear least squares or ARMA estimated by CLS)..
covinfo = arg	Information matrix method: “opg” (OPG); “hessian” (observed Hessian). (Applicable when non-legacy “optmethod=”.)
nodf	Do not perform degree of freedom corrections in computing coefficient covariance matrix. The default is to use degree of freedom corrections.
covlag=arg (default=1)	Whitening lag specification: integer (user-specified lag value), “a” (automatic selection).
covinfosel=arg (default=“aic”)	Information criterion for automatic selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn) (if “lag=a”).
covmaxlag=integer	Maximum lag-length for automatic selection (optional) (if “lag=a”). The default is an observation-based maximum of .
covkern=arg (default=“bart”)	Kernel shape: “none” (no kernel), “bart” (Bartlett, default), “bohman” (Bohman), “daniell” (Daniel), “parzen” (Parzen), “parzriesz” (Parzen-Riesz), “parzgeo” (Parzen-Geometric), “parzcauchy” (Parzen-Cauchy), “quadspec” (Quadratic Spectral), “trunc” (Truncated), “thamm” (Tukey-Hamming), “thann” (Tukey-Hanning), “tparz” (Tukey-Parzen).
covbw=arg (default=“fixednw”)	Kernel Bandwidth: “fixednw” (Newey-West fixed), “andrews” (Andrews automatic), “neweywest” (Newey-West automatic), number (User-specified bandwidth).
covnwlag=integer	Newey-West lag-selection parameter for use in nonparametric kernel bandwidth selection (if “covbw=neweywest”).
covbwint	Use integer portion of bandwidth.
m=integer	Set maximum number of iterations.
c=scalar	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled coefficients. The criterion will be set to the nearest value between 1e-24 and 0.2.
arma=arg	ARMA estimation method: “ml” (maximum likelihood); “gls” (generalized least squares), “cls” (conditional least squares). Not applicable to ARFIMA models which always estimate using maximum likelihood.
armastart=arg	ARMA coefficient starting values: “auto” (automatic) “fixed” (legacy EViews fixed); “random” (random draw); “user” (user-specified). Applicable when “arma=ml” or “arma=gls”.
s	Use the current coefficient values in estimator coefficient vector as starting values for equations specified by list with AR or MA terms when “arma=cls” (see also param ).
s=number	Determine starting values for equations specified by list with AR or MA terms when “arma=cls”. Specify a number between zero and one representing the fraction of preliminary least squares estimates computed without AR or MA terms to be used. Note that out of range values are set to “s=1”. Specifying “s=0” initializes coefficients to zero. By default EViews uses “s=1”. Does not apply to coefficients for AR and MA terms which are set to EViews determined default values.
numericderiv / ‑numericderiv	[Do / do not] use numeric derivatives only. If omitted, EViews will follow the global default.
fastderiv / ‑fastderiv	[Do / do not] use fast derivative computation. If omitted, EViews will follow the global default. Available only for legacy estimation (“optmeth=legacy”).
cov=arg	Covariance method: “ordinary” (default method based on inverse of the estimated information matrix), “huber” or “white” (Huber-White sandwich method available for nonlinear least squares or ARMA estimated by CLS), “hac” (Newey-West HAC, available for nonlinear least squares or ARMA estimated by CLS)., “hc” (extended heteroskedasticity consistent), “hcuser” (user-specified heteroskedasticity), “cr” (cluster robust). The extended “hc” methods are only available for linear specifications.
hctype=arg (default “hc2”)	Extended heteroskedasticity consistent method: “hc0” (no d.f. adjustment), “hc1” (d.f. adjusted), “hc2”, “hc3”, “hc4”, “hc4m”, “hc5”, when “cov=hc”.
userwt=arg	Name of series containing user-diagonal weights (if “cov=hcuser”)
crtype=arg (default “cr1”)	Cluster robust weighting method: “cr0” (no finite sample correction), “cr1” (finite sample correction), “hc2”, “hc3”, “hc4”, “hc4m”, “hc5”, when “cov=cr”.
crname=arg	Cluster robust series name, when “cov=cr”.
k=arg (default = 0.7)	Parameter for “cov=hc, hctype=hc5” or “cov=cr, crtype=cr5”.
k1=arg (default = 1.0)	Parameter for “cov=hc, hctype=hc4m” or “cov=cr, crtype=cr4m”.
k2=arg (default = 1.5)	Parameter for “cov=hc, hctype=hc4m” or “cov=cr, crtype=cr4m”.
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
prompt	Force the dialog to appear from within a program.
p	Print estimation results.

noiis	Do not search for impulse terms.
sis	Search for step-shift terms.
trend	Search for trend terms.
pval=number (default = 0.05)	Set the terminal condition p-value used to determine the stopping point of each search path
nolm	Do not perform AR LM diagnostic test.
arpval=number (default = 0.025)	Set p-value used in AR LM diagnostic test.
arlags=int (default = 1)	Set number of lags used in AR LM diagnostic test.
noarch	Do not perform ARCH LM diagnostic test.
archpval=number (default = 0.025)	Set p-value used in ARCH LM diagnostic test.
archlags=int (default = 1)	Set number of lags used in ARCH LM diagnostic test.
nojb	Do not perform Jarque-Bera normality diagnostic test.
jbpval=number (default = 0.025)	Set p-value used in Jarque-Bera normality diagnostic test.
nopet	Do not perform Parsimonious Encompassing diagnostic test.
petpval=number (default = 0.025)	Set p-value used in Parsimonious Encompassing diagnostic test.
nogum	Do not include the general model as a candidate for model selection.
noempty	Do not include the empty model as a candidate for model selection.
ic =arg	Set the information criterion used in model selection: “AIC” (Akaike information criteria, default), “BIC” (Schwarz information criteria), “HQ” (Hannan-Quin criteria).
blocks=int	Override the EViews’ determination of the number of blocks in which to split the estimation sample.

cx=arg	Cross-section effects: (default) none, fixed effects (“cx=f”), random effects (“cx=r”).
per=arg	Period effects: (default) none, fixed effects (“per=f”), random effects (“per=r”).
wgt=arg	GLS weighting: (default) none, cross-section system weights (“wgt=cxsur”), period system weights (“wgt=persur”), cross-section diagonal weighs (“wgt=cxdiag”), period diagonal weights (“wgt=perdiag”).
cov=arg	Coefficient covariance method: (default) ordinary, White cross-section system (period clustering) robust (“cov=cxwhite” or “cov=percluster”), White period system (cross-section clustering) robust (“cov=perwhite” or “cov=cxcluster”), White heteroskedasticity robust (“cov=stackedwhite”), White two-way cluster robust (cov=bothcluster”), Cross-section system robust/PCSE (“cov=cxsur”), Period system robust/PCSE (“cov=persur”), Cross-section heteroskedasticity robust/PCSE (“cov=cxdiag”), Period heteroskedasticity robust/PCSE (“cov=perdiag”).
keepwgts	Keep full set of GLS weights used in estimation with object, if applicable (by default, only small memory weights are saved).
rancalc=arg (default=“sa”)	Random component method: Swamy-Arora (“rancalc=sa”), Wansbeek-Kapteyn (“rancalc=wk”), Wallace-Hussain (“rancalc=wh”).
nodf	Do not perform degree of freedom corrections in computing coefficient covariance matrix. The default is to use degree of freedom corrections.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
iter=arg (default= “onec”)	Iteration control for GLS specifications: perform one weight iteration, then iterate coefficients to convergence (“iter=onec”), iterate weights and coefficients simultaneously to convergence (“iter=sim”), iterate weights and coefficients sequentially to convergence (“iter=seq”), perform one weight iteration, then one coefficient step (“iter=oneb”). Note that random effects models currently do not permit weight iteration to convergence.
unbalsur	Compute SUR factorization in unbalanced data using the subset of available observations for a cluster.
m=integer	Set maximum number of iterations.
c=scalar	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled coefficients. The criterion will be set to the nearest value between 1e-24 and 0.2.
s	Use the current coefficient values in estimator coefficient vector as starting values for equations specified by list with AR terms (see also param ).
s=number	Determine starting values for equations specified by list with AR terms. Specify a number between zero and one representing the fraction of preliminary least squares estimates computed without AR terms to be used. Note that out of range values are set to “s=1”. Specifying “s=0” initializes coefficients to zero. By default EViews uses “s=1”. Does not apply to coefficients for AR terms which are instead set to EViews determined default values.
numericderiv / ‑numericderiv	[Do / do not] use numeric derivatives only. If omitted, EViews will follow the global default.
fastderiv / ‑fastderiv	[Do / do not] use fast derivative computation. If omitted, EViews will follow the global default.
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
prompt	Force the dialog to appear from within a program.
p	Print basic estimation results.

raw	Do not use partial residuals.
nofit	Do not include a line of fit on the graphs
prompt	Force the dialog to appear from within a program.

type=arg (default= “coef”)	Type of result to save: coefficients (“coef”), residuals (“res”), bias (“bias”), covariances involving a single coefficient (“cov”), correlations involving a single coefficient (“cor”), confidence intervals (“ci”). If saving covariances or correlations, you may identify the coefficient of interest using the “coefid=” option.
wf	Make output of workfile length. Note: this option is only relevant if estimation was evaluated over the functional coefficient variable values.
derivs	Include derivative coefficients as part of the output (for all but “type=resid”). Use derivative coefficients are part of the calculation (when type=resid”).
nodups	Duplicate observations for in the set of functional coefficient evaluation points are removed.
sort	Rows of the output matrix are sorted in increasing order of the functional coefficient evaluation points.

o (default)	Ordinary residuals.
s	Standardized residuals (available only after weighted estimation and GARCH, binary, ordered, censored, and count models).
g (default for ordered models)	Generalized residuals (available only for binary, ordered, censored, and count models).
prompt	Force the dialog to appear from within a program.

type=arg (default=“pred”)	Type of regime probability to compute: one-step ahead predicted (“pred”), filtered (“filt”), smoothed (“smooth”).
n=arg	(optional) Name of group to contain the saved regime probabilities.
prompt	Force the dialog to appear from within a program.

type=arg (default=“trans”)	Transition probability results to save: transition probabilities (“trans”), expected durations (“expect”).
out=arg (default=“series”)	Output format: series (“series”) or matrix (“mat”). If saved as a matrix, only a single transition matrix will be saved using the date specified by “obs=”.
obs=arg	Date/observation used to evaluate the transition probabilities if saving results as a matrix (“out=mat”). If no observation is specified, EViews will use the first date of the estimation sample to evaluate the transition probabilities. Note that if the transition probabilities are time-invariant, setting the observation will have no effect on the content of the saved results.
n=arg	(optional) Name of group to contain the saved transition probabilities.
prompt	Force the dialog to appear from within a program.

midwgt=arg	MIDAS weight method: step function(“step”), normalized exponential Almon (“expalmon”), normalized beta function (“beta”), U-MIDAS (“umidas”), Auto-search/GETS (“autogets”) or the default Almon/PDL weighting (“almon”).
lag=arg	Method for specifying the number of lags of the high frequency regressor to use: lag selection (“auto”), fixed (“fixed”). The default is “lag=fixed”.
maxlag=arg	Maximum number of lags of the high frequency regressor to use when using lag selection. For use when “lag=auto”. The default value is 4.
fixedlag=arg	Fixed number of lags of the high frequency regressor to use. For use when “lags=fixed”. The default value is 4.
steps=integer	Stepsize (number of high frequency periods to group). For use when “midwgt=step”.
polynomial=integer	Polynomial degree. For use when Almon/PDL weighting is employed.
beta=arg	Beta function restriction: none (“none”), trend coefficient equals 1 (“trend”), endpoints coefficient equals 0 (“endpoint”), both trend and endpoints restriction (“both”). For use when “midwgt=beta”. The default is “beta=none”.
optmethod = arg	Optimization method for nonlinear estimation: “bfgs” (BFGS); “newton” (Newton-Raphson), “opg” or “bhhh” (OPG or BHHH), “hybrid” (initial BHHH followed by BFGS). Hybrid is the default method.
optstep = arg	Step method for nonlinear estimation: “marquardt” (Marquardt); “dogleg” (Dogleg); “linesearch” (Line search). Marquardt is the default method.
cov=arg	Covariance method for nonlinear models: “ordinary” (default method based on inverse of the estimated information matrix), “huber” or “white” (Huber-White sandwich).
covinfo = arg	Information matrix method for nonlinear models: “opg” (OPG); “hessian” (observed Hessian).
freq = key	Set the frequency conversion method. Key can be “first” (the higher frequency data are used from the first observation in the lower frequency period), “last” (default, the higher frequency data are used from the last observation in the lower frequency), or “match” (a specific date matching series from each page is used).
freqsrc = arg	Set the source date matching series. Only applies if freq=match is used.
freqdest = arg	Set the destination date matching series. Only applies if freq=match is used.
nodf	Do not perform degree of freedom corrections in computing coefficient covariance matrix. The default is to use degree of freedom corrections.
m=integer	Set maximum number of iterations.
c=scalar	Set convergence criterion. The criterion is based upon the maximum of the percentage changes in the scaled coefficients. The criterion will be set to the nearest value between 1e-24 and 0.2.
s	Use the current coefficient values in estimator coefficient vector as starting values in nonlinear estimation (see also param).
s=number	Determine starting values for nonlinear estimation.. Specify a number between zero and one representing the fraction of preliminary EViews chosen values. Note that out of range values are set to “s=1”. Specifying “s=0” initializes coefficients to zero. By default EViews uses “s=1”.
showopts / ‑showopts	[Do / do not] display the starting coefficient values and estimation options in the estimation output.
coef=arg	Specify the name of the coefficient vector (if specified by list); the default behavior is to use the “C” coefficient vector.
prompt	Force the dialog to appear from within a program.
p	Print estimation results.

method=arg (default=“seqplus1”)	Breakpoint testing method: “seqplus1” (sequential tests of single versus breaks), “seqall” (sequential test of all possible versus breaks), “glob” (tests of global vs. no breaks), “globplus1” (tests of versus globally determined breaks), “globinfo” (information criteria evaluation).
trim=arg (default=5)	Trimming percentage for determining minimum segment size (5, 10, 15, 20, 25).
maxbreaks=integer (default=5)	Maximum number of breakpoints to allow (not applicable if “method=seqall”).
maxlevels=integer (default=5)	Maximum number of break levels to consider in sequential testing (applicable when “method=sequall”).
size=arg (default=5)	Test sizes for use in sequential determination and final test evaluation (10, 5, 2.5, 1) corresponding to 0.10, 0.05, 0.025, 0.01, respectively
heterr	Assume regimes specific error distributions in variance computation.
commondata	Assume a common distribution for the data across segments (only applicable if original equation is estimated with a robust covariance method, “heterr” is not specified).
prompt	Force the dialog to appear from within a program.
p	Print the view.