midas
Estimates an equation using Mixed Data Sampling (MIDAS) regression.
MIDAS regression is an estimation technique which allows for data sampled at different frequencies to be used in the same regression.
Syntax
eq_name.midas(options) y x1 [x2 x3 ...] @ z1page\z1 [z2page\z2 ...]
where y, x1, etc., are the dependent and explanatory variables in the current page frequency, and z1page\z1 and z2page\z2 are the high frequency variable page\series specification.
You may not include ARMA terms in a MIDAS regression.
Options
General options

 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.
Auto-search/GETS options

 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.
Examples
equation eq1.midas(fixedlag=9, midwgt=beta, beta=endpoint) realgdp c realgdp(-1) @ monthlypage\emp(-5)
estimates a MIDAS beta weight specification using the low frequency dependent variable REALGDP and regressors C and REALGDP(-1), and 9 beta weighted lags of EMP(-5) from the “monthlypage” workfile page. The beta weight function places zero restrictions on the endpoint coefficient.
equation eq2.midas(maxlag=12, lag=auto) realgdp c realgdp(-1) @ monthlypage\emp(-5)
estimates the same equation using PDL/Almon weights. The number of lags is chosen automatically with a maximum of 12 lags.
Cross-references
“Midas Regression” discusses the specification and estimation of MIDAS regression models in EViews.