PROC VARMAX: Functional Summary :: SAS/ETS(R) 9.22 User's Guide

The VARMAX Procedure

Functional Summary

The statements and options used with the VARMAX procedure are summarized in the following table:

Table 32.1 VARMAX Functional Summary
Description	Statement	Option
Data Set Options
specify the input data set	VARMAX	DATA=
write parameter estimates to an output data set	VARMAX	OUTEST=
include covariances in the OUTEST= data set	VARMAX	OUTCOV
write the diagnostic checking tests for a model and the cointegration test results to an output data set	VARMAX	OUTSTAT=
write actuals, predictions, residuals, and confidence limits to an output data set	OUTPUT	OUT=
write the conditional covariance matrix to an output data set	GARCH	OUTHT=
BY Groups
specify BY-group processing	BY
ID Variable
specify identifying variable	ID
specify the time interval between observations	ID	INTERVAL=
control the alignment of SAS Date values	ID	ALIGN=
Options to Control the Optimization Process
specify the optimization options	NLOPTIONS
Printing Control Options
specify how many lags to print results	MODEL	LAGMAX=
suppress the printed output	MODEL	NOPRINT
request all printing options	MODEL	PRINTALL
request the printing format	MODEL	PRINTFORM=
controls plots produced through ODS GRAPHICS	VARMAX	PLOTS=
PRINT= Option
print the correlation matrix of parameter estimates	MODEL	CORRB
print the cross-correlation matrices of independent variables	MODEL	CORRX
print the cross-correlation matrices of dependent variables	MODEL	CORRY
print the covariance matrices of prediction errors	MODEL	COVPE
print the cross-covariance matrices of the independent variables	MODEL	COVX
print the cross-covariance matrices of the dependent variables	MODEL	COVY
print the covariance matrix of parameter estimates	MODEL	COVB
print the decomposition of the prediction error covariance matrix	MODEL	DECOMPOSE
print the residual diagnostics	MODEL	DIAGNOSE
print the contemporaneous relationships among the components of the vector time series	MODEL	DYNAMIC
print the parameter estimates	MODEL	ESTIMATES
print the infinite order AR representation	MODEL	IARR
print the impulse response function	MODEL	IMPULSE=
print the impulse response function in the transfer function	MODEL	IMPULSX=
print the partial autoregressive coefficient matrices	MODEL	PARCOEF
print the partial canonical correlation matrices	MODEL	PCANCORR
print the partial correlation matrices	MODEL	PCORR
print the eigenvalues of the companion matrix	MODEL	ROOTS
print the Yule-Walker estimates	MODEL	YW
Model Estimation and Order Selection Options
center the dependent variables	MODEL	CENTER
specify the degrees of differencing for the specified model variables	MODEL	DIF=
specify the degrees of differencing for all independent variables	MODEL	DIFX=
specify the degrees of differencing for all dependent variables	MODEL	DIFY=
specify the vector error correction model	MODEL	ECM=
specify the estimation method	MODEL	METHOD=
select the tentative order	MODEL	MINIC=
suppress the current values of independent variables	MODEL	NOCURRENTX
suppress the intercept parameters	MODEL	NOINT
specify the number of seasonal periods	MODEL	NSEASON=
specify the order of autoregressive polynomial	MODEL	P=
specify the Bayesian prior model	MODEL	PRIOR=
specify the order of moving-average polynomial	MODEL	Q=
center the seasonal dummies	MODEL	SCENTER
specify the degree of time trend polynomial	MODEL	TREND=
specify the denominator for error covariance matrix estimates	MODEL	VARDEF=
specify the lag order of independent variables	MODEL	XLAG=
GARCH Related Options
specify the GARCH-type model	GARCH	FORM=
specify the order of the GARCH polynomial	GARCH	P=
specify the order of the ARCH polynomial	GARCH	Q=
Cointegration Related Options
print the results from the weak exogeneity test of the long-run parameters	COINTEG	EXOGENEITY
specify the restriction on the cointegrated coefficient matrix	COINTEG	H=
specify the restriction on the adjustment coefficient matrix	COINTEG	J=
specify the variable name whose cointegrating vectors are normalized	COINTEG	NORMALIZE=
specify a cointegration rank	COINTEG	RANK=
print the Johansen cointegration rank test	MODEL	COINTTEST=
		(JOHANSEN= )
print the Stock-Watson common trends test	MODEL	COINTTEST=(SW= )
print the Dickey-Fuller unit root test	MODEL	DFTEST=
Tests and Restrictions on Parameters
test the Granger causality	CAUSAL	GROUP1=
		GROUP2=
place and test restrictions on parameter estimates	RESTRICT
test hypotheses on parameter estimates	TEST
Forecasting Control Options
specify the size of confidence limits for forecasting	OUTPUT	ALPHA=
start forecasting before end of the input data	OUTPUT	BACK=
specify how many periods to forecast	OUTPUT	LEAD=
suppress the printed forecasts	OUTPUT	NOPRINT

Top of Page