To declare a series, use the keyword series or alpha followed by a name, and optionally, by an “=” sign and a valid numeric series expression:

If there is no assignment, the series will be initialized to contain NAs.

Note: to convert data between series and vectors, see “Copying Data Between Matrices and Series/Groups”, stom, stomna, mtos.

Graph creation views are discussed in detail in “Graph Creation Command Summary”.

You can declare a series in the usual fashion:

Note that the last example above involves a series expression so that B(1) is treated as a one-period lead of the entire series, not as an element operator. In contrast:

evaluates the first observation on B in the workfile.

Once a series is declared, views and procs are available:

To access individual values:

Follow the adjust keyword with an expression made up of a combination of transform, operator, values and interpolation components. transform is used to specify a transformation of the data to which the adjustment will be made. The operator contains a mathematical expression defining how you would like to adjust the values in the series. values contains the values used during that operation. Finally, the interpolation component specifies how any missing values in the values component should be filled in via interpolation.

All adjustments are made on the current workfile sample.

The following transformations are available. If a transformation is specified, any adjustments specified in the operator or interpolation components is made to the transformed data rather than the raw data.

The following operators are available:

The values component should be made up of a space delimited set of values to use during the adjustment. In addition to single numbers, you may use the following keywords as part of the values component:

The interpolation component specifies how to fill in any missing values in the values component designated for interpolation. By default a cubic spline is used for interpolation. The other available choices are show below.

The following command replaces the first four observations in the current sample of the series UNEMP with the values 2.4, 3.5, 2.9 and 1.4.

This command modifies the first ten observations in UNEMP, by replacing them with the values: 3.4, 3.15, 2.9, 3.2, 3.5, 3.7, 3.5, 3.7, 3.5, 3.7. Note that the second observation (3.15) has been interpolated, using linear interpolation, between 3.4 and 2.9. Similarly the 4th observation was interpolated between 2.9 and 3.5. Also note that the values 3.5 and 3.7 were repeated three times.

The following command replaces the log of the first observation in the current sample with 3.4 (setting the raw value equal to exp(3.4) = 29.96). The second observation is left alone (unless it contains an NA, in which case the log value is interpolated). The third observation’s logged value is replaced with 2.2. The log of the penultimate observation in the current sample is replaced with 3.9, and the last observation with 4.8. All observations between the third and the penultimate are interpolated using a cubic spline interpolation method.

This command adjusts all the observations in the current sample by adding to the existing values. The first observation has 3.4 added to it. The second has 2.9 added to it, and the third has 4.5 added. The last observation has 1.9 added to it. The values added to the observations in between are calculated via a multiplicative Catmull-Rom spline interpolation.

See Appendix B. “Enhanced Spreadsheet Editing” and “Series Adjust” for additional discussion of series adjustment.

The forecast sample will start at the observation immediately after the estimation sample (the current workfile sample). The forecast endpoint is given by either:

If omitted, the end point will be the end of the workfile range.

The commands

open the workfile “elecdmd.WF1” and then perform automatic forecasting on the series ELECDMD. The forecasts will be stored in a series called ELECDMD_F. The ARIMAX model includes exogenous regressors of REALGDP, TEMPF and a set of monthly dummy variables, created with the @expand keyword.

The number of maximum SAR terms and SMA terms are set to 1 (instead of the default 0). Model selection is used to determine the best ARMA model, with non-converged models included in the selection process.

The forecast covers 20 periods, and upon completion, EViews will display a graph of the Akaike information criteria of each of the ARMA models considered, as well as a table of each of the selection criteria, and a graph of the each of the forecasts.

See “Automatic ARIMA Forecasting” for additional discussion.

The BDS test is a Portmanteau test for time-based dependence in a series. The test may be used for testing against a variety of possible deviations from independence, including linear dependence, non-linear dependence, or chaos.

See “BDS Independence Test” for additional discussion.

The boxplotby command is no longer supported. See boxplot for the replacement categorical graph command.

Computes, and displays a graphical view of the Baxter-King fixed length symmetric, Christiano-Fitzgerald fixed length symmetric, or the Christiano-Fitzgerald full sample asymmetric band-pass filter of the series.

The view will show the original series, the cyclical component, and non-cyclical component in a single graph. For non time-varying filters, a second graph will show the frequency responses.

Follow the bpf keyword with any desired options, and the optional name to be given to the cyclical component. If you do not provide cyc_name, the filtered series will be named BPFILTER## where ## is a number chosen to ensure that the name is unique.

To display the graph, you may need to precede the object command with the “show” keyword.

Suppose we are working in a quarterly workfile and we issue the following command:

EViews will compute the Baxter-King band-pass filter of the series LGDP. The periodicity of cycles extracted ranges from 6 to 32 quarters, and the filtered series will be saved in the workfile in CYC0. The BK filter uses the default lag of 12 (3 years of quarterly data).

Since this is a fixed length filter, EViews will display both a graph of the cyclical/original/non-cyclical series, as well as the frequency response (gain) graph. To suppress the latter graph, we could enter a command containing the “nogain” option:

In this example, we have also overridden the default by specifying a fixed lag of 12 (quarters). Since we have omitted the name for the cyclical series, EViews will create a series with a name like BPFILTER01 to hold the results.

To compute the asymmetric Christiano-Fitzgerald filter, we might enter a command of the form:

The cyclical components are saved in CYC0, the non-cyclical in NON1, and the weighting matrix in WM.

See “Frequency (Band-Pass) Filter”.

See also Series::hpf.

Calculate either the rolling ADF (RADF), supremum ADF (SADF) or generalized supremum ADF (GSADF) test for the existence of a bubble in an asset.

Performs a generalized supremum bubble test on the SPY series, with an initial window length of 30 observations, using the Hannan-Quinn Criterion to determine the appropriate lag length, and using a seed value of 40 for the random number generator used in the bootstrapped p-values.

See “Explosive Bubble Tests”.

You should specify the exogenous variables and order of dependent variable differencing in the test equation using the following options:

Specifies the number of lag difference terms to be included in the test equation. The default is to perform automatic selection using the Schwarz information criterion. You may specify a fixed lag using the “lag=” option.

See “Unit Root Tests with a Breakpoint” for additional discussion.

See also Series::uroot.

The cdfplot command is no longer supported. See distplot.

Test for the presence of cross-sectional dependence in a panel series.

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 a panel series.

will compute and display the panel cross-section dependence test results.

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

Calculate the standard normal, Quandt-Andrews, Pettitt and Buishand tests for a change in the location of the distribution of a series.

Performs a change point test on the GDPC1 series, performing 19,999 bootstraps using HVK estimates in a sieve bootstrap, and saving the test statistics and p-values into a matrix object named CPSTATS.

See “Change Point Tests” for discussion.

You should the classify keyword with any desired options, a specification spec, the “@”-sign, the name to be given the output series, and optionally the name for a new valmap object describing the classification.

The form for the spec will depend on which of the four supported methods for classification is employed (using the “method=” option).

classifies the values of API5B into bins of width 100 starting at 200 and ending at the data maximum times 1.05. The classification results are saved in the series API5B_CT with associated map API5B_MP.

classifies API5B into bins of size 100 from 200 through 1100. The output series API5B_CT1 will contain values taken from the right endpoints of the classification intervals. Observations with out-of-range values will be assigned an NA.

defines 9 equally sized bins, starting at 200 and ending at 1100, and classifies the data into bin index identifiers in the series API5B_CT2 with map API5B_MP2. The bins are closed on the right, and out-of-range values will generate an error.

classifies the values of API5B into quartiles (using the Gumbel definition) in the series API5B_CT3. Observations with NA values for API5B will be encoded as 0 in the output series.

See “Generate by Classification” for additional discussion.

Removes the series’s history attribute, as shown in the label view of the series.

where start_point specifies the first of n observations to clear. If n is negative, start_point specifies the last of |n| observations to clear. For dated workfiles, start_point should be entered as a date. For panels and undated workfiles, start_point should be an observation number.

clears 10 observations starting at 1952 quarter 2.

clears 5 observations ending at observation number 10.

Removes the series’s history attribute, as shown in the label view of the series.

The first line removes the history from the series S1, and the second line displays the label view of S1, including the now blank history field.

See “Labeling Objects” for a discussion of labels and display names.

See also Series::label.

Removes the series’s remarks attribute, as shown in the label view of the series.

The first line removes the remarks from the series S1, and the second line displays the label view of S1, including the now blank remarks field.

See “Labeling Objects” for a discussion of labels and display names.

See also Series::label.

Creates either a named or unnamed copy of the series.

creates an unnamed copy of the series S1.

creates S2, a copy of the series S1.

See also copy.

Displays the autocorrelation and partial correlation functions of the series, together with the Q-statistics and p-values associated with each lag.

You must specify the largest lag n to use when computing the autocorrelations.

Displays the correlograms of the SER1 series for up to 24 lags.

See “Autocorrelations (AC)” and “Partial Autocorrelations (PAC)” for a discussion of autocorrelation and partial correlation functions, respectively.

Display the contents of a table, graph, or spool in the window of the series object.

Display the contents of the table TAB1 in the window of the object SERIES1.

Most often used in constructing an EViews Add-in. See “Custom Object Output”.

Attaches a display name to a series object which may be used to label output in tables and graphs in place of the standard series object name.

Display names are case-sensitive, and may contain a variety of characters, such as spaces, that are not allowed in series object names.

The first line attaches a display name “Hours Worked” to the series HRS, and the second line displays the label view of HRS, including its display name.

The first line attaches a display name “US Gross Domestic Product” to the series GDP. The line graph view of GDP from the second line will use the display name as the legend.

See “Labeling Objects” for a discussion of labels and display names.

See also Series::label and Series::label.

Saves the data used to display a histogram, kernel density, theoretical distribution, empirical CDF or survivor plot, or quantile plot to the workfile.

saves the distribution plot data specified by dist_type, where dist_type must be one of the following keywords:

The theoretical quantile-quantile plot type “theoryqq” takes the options described in qqplot under “Theoretical Options”.

For the remaining types, dist_options are any of the distribution type-specific options described in distplot.

Note that the graph display specific options such as “fill,” “nofill,” and “leg,” and “noline” are not relevant for this procedure.

You may use the “prompt” option to force the dialog display

creates the data used to draw a histogram from the series GDP with the anchor at 0, density scaling, and right-closed intervals, and stores that data in a matrix called MATRIX01 in the workfile.

generates the kernel density data computed with a biweight kernel at 50 grid points, using a bandwidth of 0.5 and linear binning, and stores that data in MATRIX02.

creates theoretical quantile-quantile data from the series WAGE using the ordinary quantile method to calculate quantiles. The theoretical distribution is the logit distribution, with the location parameter set to 0.5. The data is saved into the matrix MATRIX03.

For a description of distribution graphs and quantile-quantile graphs, see “Analytical Graph Types”.

See also distplot and qqplot.

You may follow the dsa keyword with a name to save the seasonally adjusted series. Further, you may use the @fa and @trnd keywords to provide names for the saved seasonal factors and the trend series.

Performs daily seasonal adjustment on the ELECDMD series, specifying that the forecast end point should be 30 June 2015, and that the final adjusted series should be named ELECDMD_ADJUSTED.

Performs daily seasonal adjustment on ELECDMD, using a fixed number of trigonometric terms in the ARIMA step, and without using day-of-month or day-of-year STL. As well as saving the final adjusted series as ELECDMD_ADJUSTED, the final seasonal factor are also saved under ELECDMD_FACTORS.

See also Series::x12, Series::x13, and “Seasonal Adjustment”.

By default, EViews displays a summary table showing the number of duplicate groups of a given size, but you may use the options to display an alternative view.

Of particular note is that the spreadsheet and individual duplicates displays are interactive - clicking on rows in one will open the display to show the other. Thus, clicking on a duplicate in the spreadsheet view will jump to show all of the observations that share that duplicate. Similarly, clicking on an observation in the shared individual duplicates view will jump to the corresponding observation in the full spreadsheet.

displays the duplicates summary for the series SER1.

displays a spreadsheet showing highlighted duplicates.

For a description of the duplicates view, see “Duplicates Analysis”.

The following options apply if iterative estimation of parameters is required:

The command

uses the default settings to test whether data in the series x for the current sample comes from a normal distribution. Both the location and scale parameters are estimated from the data in X.

See “Empirical Distribution Tests” for a description of the goodness-of-fit tests.

See also qqplot.

The ets procedure forecasts a series using the ETS model framework with state-space based likelihood calculations, support for model selection, and calculation of forecast standard errors.

The ETS framework defines an extended class of exponential smoothing models, including the standard exponential smoothing models (e.g., Holt and Holt-Winters additive and multiplicative models).

You should enter the ets keyword followed by options and then the a name for the smoothed output series. You can specify the smoothing method (the default setting is additive error, no trend, no seasonality) and the smoothing options in the parenthesis.

The forecast sample will start at the observation immediately after the estimation sample (the current workfile sample). The forecast endpoint is given by either:

One of these options is required.

smooths the series SALES using the an ANN (additive error, no trend, no seasonal) model and creates the smoothed series named “SALES_F”.

will smooth TB3, automatically selecting the best smoothing model amongst the different Error and Trend specifications (the Seasonal specification is set at none).

will smooth the series SALES using the an AAA (additive error, additive trend, additive seasonal) model and display the output in a spool object which contains the actual and decomposition series (i.e., forecast, trend, level, and seasonal series) in multiple graphs.

will smooth the series SALES using the an AAA (additive error, additive trend, additive seasonal) model, create the decomposition series named level, trend, and season series as level1, trend1, and season1, respectively, and display a spool object which contains the actual and decomposition graphs in a single graph.

will find out the best model amongst the different Error, Trend, and Seasonal specifications and present the estimation results in a spool object which contains the graphs with forecast and likelihood comparison graphs between all available models.

will search for the best model using average mean square errors calculations and display the estimation results in a spool object with forecast and likelihood comparison tables.

See “Exponential Smoothing” for a discussion of exponential smoothing methods.

See also Series::smooth.

Follow the keyword with a list of values to place in the specified object. Each value should be separated by a comma. By default, series fill ignores the current sample and fills the series from the beginning of the workfile range. You may provide sample information using options.

Running out of values before the object is completely filled is not an error; the remaining cells or observations will be unaffected, unless the “l” option is specified. If, however, you list more values than the object can hold, EViews will not modify any observations and will return an error message.

To generate a series D70 that takes the value 1, 2, and 3 for all observations from 1970:1:

Note that the last argument in the fill command above is the letter “l”. The next three lines generate a dummy series D70S that takes the value one and two for observations from 1970:1 to 1979:4:

Assuming a quarterly workfile, the following generates a dummy variable for observations in either the third and fourth quarter:

Note that this series could more easily be generated using @seas or the special workfile functions (see “Basic Date Functions”).

You should specify the forecast data to be averaged by entering a list of objects as forecast_data. The list may be a list of series objects, a group object, a series naming pattern (such as “f*” to indicate all series starting with the letter “F”), or a list of equation objects.

If a list of equations is entered, EViews will automatically forecast from those equation objects over the forecast sample (the current workfile sample).

The commands

open the workfile elecdmd.wf1 and then perform forecast averaging using the actual series ELECDMD, and the forecast series specified by the naming pattern ELECF_FE*.

The averaging method MSE is used. A training sample of 2012M1 to 2012M12 is used to calculate the weights in the MSE and MSE Ranks methods.

See “Forecast Averaging” for additional discussion.

See also Series::forceval.

You should specify the forecast data to be evaluated by entering a list of objects as forecast_data. The list may be a list of series objects, a group object, a series naming pattern (such as “f*” to indicate all series starting with the letter “F”), or a list of equation objects.

If a list of equations is entered, EViews will automatically forecast from those equation objects over the evaluation sample (the current workfile sample).

The commands

open the workfile elecdmd.wf1 and then perform forecast evaluation using the actual series ELECDMD, and the forecast series specified by the naming pattern ELECF_FE*.

The averaging methods Mean, MSE and MSE Ranks are used, with the power of the MSE Ranks method set at “2”. A training sample of 2012M1 to 2012M12 is used to calculate the weights in the MSE and MSE Ranks methods.

See “Label” for additional discussion.

See also Series::forcavg.

The freq command performs a one-way frequency tabulation.

Frequencies are computed for the current sample of observations. Observations with NAs are dropped unless included by option. You may use options to control automatic binning (grouping) of values and the order of the entries of the table.

tabulates each value (no binning) of HRS, with entries in ascending value order. The table will display counts, percentages, and cumulative frequencies.

tabulates INC including NAs. The observations will be binned if INC has more than 200 distinct values; EViews will create at most 50 equal value-width bins. The number of bins may be smaller than 50.

tabulates INC with the table rows ordered from values with highest frequency to lowest.

See “One-Way Tabulation” for a discussion of frequency tables.

Follow the frml keyword with a name for the series, and an assignment statement. The special keyword “@CLEAR” is used to return the auto-updating series to an ordinary numeric series.

To define an auto-updating numeric series, you must use the frml keyword prior to entering an assignment statement. The following example creates a series named LOW that uses a formula to compute its values.:

The auto-updating series takes the value 1 if either INC is less than or equal to 5000 or EDU is less than 13, and 0 otherwise, and will be re-evaluated whenever INC or EDU change.

You may apply a frml to an existing series. The commands:

makes the previously created series Z an auto-updating series containing the average of series X and Y. Note that once a series is defined to be auto-updating, it may not be modified directly. Here, you may not edit Z, nor may you generate values into the series.

Note that the commands:

while similar, produce quite different results, since the absence of the frml keyword in the second example means that EViews will generate fixed values in the series instead of defining a formula to compute the series values. In this latter case, the values in the series Z are fixed, and may be modified.

One particularly useful feature of auto-updating series is the ability to reference series in databases. The command:

creates a series called GDP that obtains its values from the series GDP in the database USDATA. Similarly:

creates an auto-updating series that is the log of the values of GDP in the database USDATA.

To turn off auto-updating for a series, you should use the special expression “@CLEAR” in your frml assignment. The command:

sets the series to numeric value format, freezing the contents of the series at the current values.

See “Auto-Updating Series”.

See also Link::link.

generates a numeric series that takes the values from the series X and adds 3.

See Series::series for a discussion of the expressions allowed in genr.

The hist command displays descriptive statistics and a histogram for the data in the series.

Displays the histogram and descriptive statistics of LWAGE.

See “Histogram and Stats” for a discussion of the descriptive statistics reported in the histogram view.

See distplot for a more fully-featured and customizable method of constructing histograms and Series::stats stats for a view with a more extensive set of basic descriptive statistics.

You may need to prepend the “show” keyword to display the graph the smoothed and original series.

The degree of smoothing may be specified as an option. You may specify the smoothing as a value, or using a power rule:

If no smoothing option is specified, EViews will use the power rule with a value of 2.

smooths the GDP series with a smoothing parameter “1000” and saves the smoothed series as GDP_HP.

smooths the same series with a power parameter of “4” and saves the smoothed series as GDP_HP, and the cycle series as GDP_CYCLE.

See “Hodrick-Prescott Filter” for details.

Where startpoint specifies the first or last observation from which the observations are shifted. For dated workfiles, startpoint should be entered as a date. For panels and non-dated workfiles startpoint should be an observation number.

n specifies the number of observations shifted.

Inserts 2 new observations beginning at observation 1952 quarter 2. The previous value associated with 1952Q2 will now correspond to 1952Q4.

Inserts 5 new observations ending at observation number 10 in the workfile.

The following lines interpolate the missing values of series X1 using linear interpolation, and store the new interpolated series with a name X_INTER:

This line performs the same interpolation, but this time using the Cardinal spline, with a tension value of 0.8:

See “Interpolate” for discussion.

JDemetra+ is available only for quarterly and monthly series, and only performs X-13 style seasonal adjustment.

This will execute the JDemetra+ X-13 based seasonal adjustment routine on the series HSTARTSNSA. The JDemetra+ RSA5c default specification is used, but outlier detection is turned off. The seasonal factors and seasonally adjusted data are stored into the workfile with the names HSTARTSNA_JDM_D10 and HSTARTSNA_JDM_D11 respectively.

See “JDemetra+” for discussion.

The kdensity command is no longer supported. See distplot.

As a procedure, label changes the fields in the series label.

The first version of the command displays the label view of the series. The second version may be used to modify the label. Specify one of the following options along with optional text. If there is no text provided, the specified field will be cleared.

The following lines replace the remarks field of SER1 with “Data from CPS 1988 March File”:

To append additional remarks to SER1, and then to print the label view:

To clear and then set the units field, use:

See “Labeling Objects” for a discussion of labels.

See also Series::displayname.

Examples

computes the symmetric long-run variance of the series SER1 and saves the results in the output sym matrix OUTSYM.

computes the long-run variance SER1 using the quadratic spectral kernel, Andrews automatic bandwidth.

performs the same calculation but uses AR(3) prewhitening prior to computing the kernel estimator.

computes parametric VAR estimates of the upper long-run variance using an AIC based automatic lag-length prewhitening procedure, Newey-West bandwidth selection, and row weight series RES.

Cross-references

See “Long-run Variance”, “Panel Long-run Variances”, Appendix F. “Long-run Covariance Estimation”.

See also Group::lrcov.

saves the first three principal components (in normalized loadings form) of the panel series SER1 to the workfile. The components will have variances that are proportional to the eigenvalues of the contemporaneous correlation matrix. In addition, the vector V1 and matrix M1 will contain the eigenvectors and eigenvalues of the decomposition.

saves the first principal component of the period (within cross-section) Spearman rank correlations. The scores will be normalized so that the variances of the scores are equal to 1.

See “Saving Component Scores” and “Panel Principal Components” for further discussion.

To display the results of the panel principal components decomposition, see Series::panpcomp.

Outlier Output Options

Threshold Output Options

creates the vector OUT_VAR with containing variance decomposition per scale using a DWT with maximum scale 2, and a series length adjustment by padding with median values of the series SRS.

creates vectors OUT_OLR1, OUT_OLR1, etc. with outlier identifiers using a DWT, Haar filter, soft threshold, universal threshold limit, and Gaussian median computation for the wavelet coefficient variance.

See “Wavelet Analysis” and “Wavelet Variance Decomposition” for discussion. See also “Wavelet Objects”.

See also Series::wavedecomp, Series::waveanova, Series::waveoutlier, and Series::wavethresh.

where out_name is either a name for the output series or a wildcard expression. Note that a wildcard may not be used if the original group contains series expressions.

whitens the series in GRP1 using a VAR with auto-selected number of lags based on the SIC information criterion and a maximum of 10 lags. The resulting series is named ASER1.

whitens the series using a no-constant VAR and 5 lags.

See “Make Whitened” for details.

If the optional valmap name is provided, the procedure will assign the specified value map to the series. If no name is provided, EViews will remove an existing valmap assignment.

assigns the valmap object MYMAP to SERIES1.

removes an existing valmap assignment from SERIES1.

See “Value Maps” for a discussion of valmap objects in EViews.

movereg is only available for weekly data.

You should follow the movereg command with any additive or level-shift outliers, holiday events or user variables to be included as part of the procedure. Outliers are specified as full dates or in "weeknumber year" format. Holidays are specified with one of the built-in holiday keywords, followed by its holiday weighting pattern. Available holiday keywords are: "easter", "labor", "newyear", "memorial", "taxday", "christmas", "july4th", "february", "thanksgiving", "mlking", "veterans", and "columbus".

Performs movereg seasonal adjustment on the series ICNSA, saving the adjusted data and factors under the default names ICNSA_SA and ICNSA_SAF.

Performs a seasonal adjustment with the 37th week of 2001 as an additive outlier, and specifying an adjustment for Christmas, where the Christmas effect is felt over 5 weeks, 3 weeks before Christmas through one after, with the week of Christmas and after Christmas having slightly more weight. The output holiday series is stored under ICNSA_HOL.

See “Object Linking and Embedding (OLE)” for a discussion of using OLE with EViews.

Use Tukey fences, mean/standard deviation fences, wavelet outliers, or ARMA outliers detection methods to identify observations that deviate from the natural pattern of the underlying series.

Performs outlier detection on the cycle series from a Hodrick-Prescott filter of the GDPC1 series, opting to not use Wavelet Outlier detection, and setting the sensitivity of the detection to "high", but overwriting the k value used in the mean/standard deviation fence to 3.

See “Outlier Detection”. See also Equation::fitoutliers.

You may compute measures related to Pearson product-moment (ordinary) covariances and correlations, Spearman rank covariances, or Kendall’s tau along with test statistics for evaluating whether the correlations are equal to zero.

By default, EViews will compute the contemporaneous (between cross-section) covariances, correlations and related statistics for the panel series. You may use the “period” option to instruct EViews to compute the between period (within cross-section) measures.

You should specify keywords indicating the statistics you wish to display from the list below.

You may specify keywords from one of the four sets (Pearson correlation, Spearman rank correlation, Kendall’s tau, Uncentered Pearson) corresponding the computational method you wish to employ. (You may not select keywords from more than one set.)

If you do not specify keywords, EViews will assume “cov” and compute the Pearson covariance matrix.

Note that cases and obs are available for each of the methods.

displays the contemporaneous Pearson covariance matrix of SER1 using the cross-sections in sample.

displays a table containing the contemporaneous Pearson correlation matrix for SER1, along with t-statistics for testing for zero correlation, and associated p-values,.

computes the between period Kendall’s tau-b, score statistic, and p-value for the score statistic, for the periods in the sample “1990 2010” using samples with pairwise missing value exclusion.

computes the contemporaneous Pearson correlation for the series SER1, displays it in list form, and saves the results in the symmetric matrix object AACORR.

See “Covariance Analysis” and “Panel Covariances”for discussion.

To display the results of the panel principal components decomposition, see Series::panpcomp.

See Group::cor for the command to compute these measures across series.

where the elements to display in loadings, scores, and biplot graph form (“out=loadings”, “out=scores” or “out=biplot”) are given by the optional indices, (e.g., “1 2 3” or “2 3”). If indices is not provided, the first two elements will be displayed.

The number of elements to display in the table and eigenvalue graph form is given by the minimum of the elements specified using the “n=”, “mineigen=” and “cproport=” options.

The default eigenvalue graph shows a scree plot of the ordered eigenvalues. You may use the “scree”, “cproport”, and “diff” option keywords to display any combination of the scree plot, cumulative eigenvalue proportions plot, or eigenvalue difference plot.

computes the principal components decomposition of the contemporaneous (between cross-section) Pearson correlation matrix for the series SER1.

The output view is stored in a table named tab1, the eigenvalues in a vector named v1, and the eigenvectors in a matrix named m1.

displays a screen plot of the eigenvalues, and a graph containing both a screen plot and a plot of the cumulative eigenvalue proportions.

displays a loadings plot for the principal component decomposition of the period (within cross-section) Spearman rank correlation matrix, and

displays a symmetric biplot of the period Spearman correlation matrix for all three pairwise comparisons.

See “Principal Components” and “Panel Principal Components” for further discussion.

To compute principal components scores and save them in series in the workfile, see Series::makepanpcomp.

Prophet requires the Prophet Python library installed with EViews.

Enter a name for the forecast series, and optionally, a name for the lower and upper bounds of the forecast.

The forecast sample will start at the observation immediately after the estimation sample (the current workfile sample). The forecast endpoint is given by either:

If omitted, the end point will be the end of the workfile range.

This will execute the Facebook Prophet routine on the ELECDMD series, inserting the actual values for out-of-forecast sample observations. The forecasted values will be stored in the new series ELEC_F, with the lower and upper bounds to the forecast being stored in ELEC_L and ELEC_U respectively.

See “Facebook Prophet Forecasting”.

You should follow the resample keyword and options with, if desired, an output_spec containing a list of names or a wildcard expression identifying the series to hold the output. If a list is used to identify the targets, the number of target series must match the number of names implied by the keyword.

creates a new series SER1_B by drawing with replacement from the rows of SER1 in the current workfile sample. If SER1_B already exists in the workfile, it will be overwritten if it is a series objects, otherwise EViews will error. Note that only values of SER_B (in this case the current workfile sample) will be overwritten.

will append “_2” to the SER1 for the name of the new series, SER_2. The rows in the sample will be drawn with probabilities proportional to the corresponding values in the series WT. WT must have non-missing non-negative values in the current workfile sample.

See “Resample” for a discussion of the resampling procedure. For additional discussion of wildcards, see Appendix A. “Wildcards”.

See also @resample and @permute for sampling from matrices.

The seas command carries out seasonal adjustment using either the ratio to moving average, or the difference from moving average technique.

EViews also performs Census X11, Census X12, and Census X-13ARIMA-SEATS seasonal adjustment. For details, see Series::x11, Series::x12, and Series::x13.

seasonally adjusts the series SALES using the multiplicative method and saves the adjusted series as ADJ_SALES.

See “Seasonal Adjustment” for a discussion of seasonal adjustment methods.

See also seasplot, Series::x11, Series::x12, Series::x13, and Series::tramoseats.

Computes Hylleberg, Engle, Granger, and Yoo (HEGY, 1990) test, Smith and Taylor (1998) likelihood HEGY test, Canova and Hansen (CH, 1995), and Taylor (2005) HEGY variance ratio tests.

Specifies the number of lag difference terms to be included in the test equation. Applicable in “Summary”, LLC, Breitung, IPS, and Fisher-ADF tests. The default setting is to perform automatic lag selection using the Schwarz criteria (“lagmethod=sic”).

runs a traditional HEGY test using seasonal dummies and trend and automatic AIC lag selection.

runs likelihood HEGY test using spectral intercepts and trends and automatic SIC lag selection.

does Canova-Hansen test for frequency 0 and PI, and add lag of dependent variable as regressor.

See “Seasonal Unit Root Testing” for a discussion of seasonal unit root testing.

The series command creates and optionally initializes a series, or modifies an existing series.

The series command should be followed by either the name of a new series, or an explicit or implicit expression for generating a series. If you create a series and do not initialize it, the series will be filled with NAs. Rules for composing a formula are given in “Numeric Expressions”.

creates a series named X filled with NAs.

Once a series is declared, you do not need to include the series keyword prior to entering the formula. The following example generates a series named LOW that takes value 1 if either INC is less than or equal to 5000 or EDU is less than 13, and 0 otherwise.

This example solves for the implicit relation and generates a series named Z which is the double log of Y so that Z=log(log(Y)).

The command:

creates a series named Z which is the average of series X and Y.

generates a series named CWAGE which is equal to WAGE if HRS exceeds 5, and zero otherwise.

generates a series named Z which is the base 10 log of Y.

The commands:

generate a series named Y_T which replaces negative values of Y with NAs.

creates a series named Z which is the centered moving average of the series X with two leads and two lags.

generates a series named Z which is the centered moving average of the series X over twelve periods.

creates a series named Y which is a random draw from a uniform distribution between 2 and 5.

generates a series named Y which is a random draw from a normal distribution with mean 3 and variance 5.

There is an extensive set of functions that you may use with series:

See “Numeric Expressions” for a discussion of rules for forming EViews expressions.

Sets the attribute attr to attr_value. Note that quoting the arguments may be required. Once added to an object, the attribute may be extracted using the @attr data member.

sets the “revised” attribute in the object A to the string “never”, and extracts the attribute into the string object S.

See “Adding Custom Attributes in the Label View” and “Adding Your Own Label Attributes”.

Determines the default frequency conversion method for a series when copied or linked between different frequency workfiles.

You may override this default conversion method by specifying a frequency conversion method as an option in the specific command (using copy or fetch or Link::linkto).

If you do not set a conversion method and if you do not specify a conversion method as an option in the command, EViews will use the conversion method set in the global option.

Follow the series name with a period, the keyword, and option letters to specify the frequency conversion method. If either the up-conversion or down-conversion method is omitted, EViews will set the corresponding method to Use EViews default.

The following options control the frequency conversion method when copying series and group objects to a workfile, converting from low to high frequency:

The following options control the frequency conversion method when copying series and group objects to a workfile, converting from high to low frequency:

sets the default down-conversion method of the series UNEMP to take the average of nonmissing observations, and resets the up-conversion method to use the global default.

sets the default down-conversion method for IBM_HI to take the largest observation of the higher frequency observations, propagating missing values, and the default up-conversion method to constant, match sum.

resets both methods to the global default.

See “Frequency Conversion” for a discussion of frequency conversion and the treatment of missing values.

See also copy and fetch, and Link::linkto.

where:

To specify the series or expression whose values will determine the background color:

where spec is a series name or expression.

To specify the minimum and maximum values where the coloring begins and ends:

To set the missing value (NA) background color:

where color_arg is described below in “Color definitions”. If omitted, the color defaults to “white”.

There are optional type-specific arguments that correspond to each of the type choices:

To set the single background color:

where color_arg is described below in “Color definitions”. If omitted, the color defaults to “white”.

You may set the color for both the non-negative (posclr) and the negative (negclr) values

where color_arg is described below in “Color definitions”. If omitted, the non-negative color defaults to “white” and the negative color defaults to light-red.

To specify the range, you must specify the range endpoints:

where range_def specifies the range endpoints:

By default, the range will be open on the lower and closed on the upper threshold limits.

You should provide a color specification for the inside range color (inclr) and outside range color (outclr):

where color_arg is described below in “Color definitions”. If omitted, the interior color defaults to light-red, and the exterior defaults to white.

When “type=hilo” you may specify the high, low, and median coloring values:

where color_arg is described below in “Color definitions”. If omitted, the colors default to light-red.

When “type=custom” you may specify custom coloring options.

You may optionally set a base background color, and then add one or more custom threshold or range color specifications. Multiple threshold and range specifications will layer, with the first applied first, followed by the second, and so on.

To set the base color (optional):

as described below in “Color definitions”. If omitted, the color defaults to “white”.

To add a threshold specification:

where threshold_spec is one of

and the below_arg and above_arg are one of

and color_arg are as described below in “Color definitions”. If omitted, the color defaults to “white”.

The optional threshold_name argument may be used to attach a name to the corresponding definition.

To add a range specification:

where range_spec is one of

outside_arg is one of

color_arg1 and color_arg2 are as described below in “Color definitions”.

The optional range_name argument may be used to attach a name to the corresponding definition.

color_arg specifies the color to be employed in the arguments above. The color may be specified using predefined color names, by specifying the individual red-green-blue (RGB) components using the special “@RGB” function, or by specifying the individual red-green-blue (RGB) components in hexadecimal using the special “@HEX” function.

The predefined colors are given by the keywords (with their RGB and HEX equivalents):

To set a gray background color for all cells in the spreadsheet, you may use:

To set a background color for negative values, you may use

which sets the background sheet fill color to white for non-negative values and light red for negative values of SER1.

Similarly,

sets the background sheet fill color to @rgb(10, 20, 30) for non-negative values and purple for negative values of SER1.

Range coloring may be specified using the “type=range” option. The command

sets the background fill to @rgb(128, 0, 128) for values between 10 and 20, light-red to values outside of the range 10 to 20, and green, for missing values.

Custom coloring allows you to construct more complex background filling:

See “Value-Based Text and Fill Coloring”.

See also Series::settextcolor.

where format_arg is a set of arguments used to specify format settings. If necessary, you should enclose the format_arg in double quotes.

For series, setformat operates on all of the cells in the series.

To format numeric values, you should use one of the following format specifications:

To specify a format that groups digits into thousands using a comma separator, place a “t” after the format character. For example, to obtain a fixed number of decimal places with commas used to separate thousands, use “ft[.precision]”.

To use the period character to separate thousands and commas to denote decimal places, use “..” (two periods) when specifying the precision. For example, to obtain a fixed number of characters with a period used to separate thousands, use “ct[..precision]”.

If you wish to display negative numbers surrounded by parentheses (i.e., display the number -37.2 as “(37.2)”), you should enclose the format string in “()” (e.g., “f(.8)”).

To format numeric values using date and time formats, you may use a subset of the possible date format strings (see “Date Formats”). The possible format arguments, along with an example of the date number 730856.944793113 (January 7, 2002 10:40:30.125 p.m) formatted using the argument are given by:

Note that the “hh” formats display 24-hour time without leading zeros. In our examples above, there is no difference between the “HH” and “hh” formats for 10 p.m.

Also note that all of the “YYYY” formats above may be displayed using two-digit year “YY” format.

To set the format for all cells in the series to fixed 5-digit precision, simply provide the format specification:

Other format specifications include:

You may use any of the date formats given above:

to set the series display characteristics.

See Series::setwidth, Series::setindent and Series::setjust for details on setting spreadsheet widths, indentation and justification.

where indent_arg is an indent value specified in 1/5 of a width unit. The width unit is computed from representative characters in the default font for the current spreadsheet (the EViews spreadsheet default font at the time the spreadsheet was created), and corresponds roughly to a single character. Indentation is only relevant for non-center justified cells.

The default indentation setttings are taken from the Global Defaults for spreadsheet views ( “Spreadsheet Data Display”) at the time the spreadsheet was created.

For series, setindent operates on all of the cells in the series.

To set the indentation for a series object:

See Series::setwidth and Series::setjust for details on setting spreadsheet widths and justification.

where format_arg may be set to left, center, right, or auto (strings are left-justified and numbers are right-justified). Default display settings can be set in General Options; see “Spreadsheet Data Display”.

left-justifies the cells in the spreadsheet view of the series SER1.

See Series::setwidth and Series::setindent for details on setting spreadsheet widths and indentation.

where:

To specify the series or expression whose values will determine the background color:

where spec is a series name or expression.

To specify the minimum and maximum values where the coloring begins and ends:

To set the missing value (NA) background color:

where color_arg is described below in “Color definitions”. If omitted, the color defaults to “black”.

There are optional type-specific arguments that correspond to each of the type choices:

To set the single text color:

where color_arg is described below in “Color definitions”. If omitted, the color defaults to “black”.

You may set the color for both the non-negative (posclr) and the negative (negclr) values

where color_arg is described below in “Color definitions”. If omitted, the non-negative color defaults to “black” and the negative color defaults to “red”.

To specify the range, you must specify the range endpoints:

where range_def specifies the range endpoints:

By default, the range will be open on the lower and closed on the upper threshold limits.

You should provide a color specification for the inside range color (inclr) and outside range color (outclr):

where color_arg is described below in “Color definitions”. If omitted, the interior color defaults to light-red, and the exterior defaults to white.

When “type=hilo” you may specify the high, low, and median coloring values:

where color_arg is described below in “Color definitions”. If omitted, the colors default to light-red.

When “type=custom” you may specify custom coloring options.

You may optionally set a base text color, and then add one or more custom threshold or range color specifications. Multiple threshold and range specifications will layer, with the first applied first, followed by the second, and so on.

To set the base color (optional):

as described below in “Color definitions”. If omitted, the color defaults to “white”.

To add a threshold specification:

where threshold_spec is one of

and the below_arg and above_arg are one of

and color_arg are as described below in “Color definitions”. If omitted, the color defaults to “white”.

The optional threshold_name argument may be used to attach a name to the corresponding definition.

To add a range specification:

where range_spec is one of

outside_arg is one of

color_arg1 and color_arg2 are as described below in “Color definitions”.

The optional range_name argument may be used to attach a name to the corresponding definition.

color_arg specifies the color to be employed in the arguments above. The color may be specified using predefined color names, by specifying the individual red-green-blue (RGB) components using the special “@RGB” function, or by specifying the individual red-green-blue (RGB) components in hexadecimal using the special “@HEX” function.

The predefined colors are given by the keywords (with their RGB and HEX equivalents):

To set a gray text color for all cells in the spreadsheet, you may use:

To set a text color for negative values, you may use

which sets the text color to black for non-negative values and red for negative values of SER1.

Similarly,

sets the text color to @rgb(10, 20, 30) for non-negative values and purple for negative values of SER1.

Range coloring may be specified using the “type=range” option. The command

sets the text to @rgb(128, 0, 128) for values between 10 and 20, light-red to values outside of the range 10 to 20, and green, for missing values.

Custom coloring allows you to construct more complex text coloring:

See “Value-Based Text and Fill Coloring”.

See also Series::setfillcolor.

where width_arg specifies the width unit value. The width unit is computed from representative characters in the default font for the current spreadsheet (the EViews spreadsheet default font at the time the spreadsheet was created), and corresponds roughly to a single character. width_arg values may be non-integer values with resolution up to 1/10 of a width unit.

sets the width of series SER1 to 12 width units.

See Series::setindent and Series::setjust for details on setting spreadsheet indentation and justification.