You can tell SAS in this PROC what the correct lag for the AR is (or what you think it is anyhow]. Signficance tests are generated for the AR tested in this PROC, but I do not know which test is being performed on them. Does anyone know?
There are a variety of ways to tell if the residuals are white noise, Box-Ljung and Breusch-Godfrey are the two I know of (I guess Durbin's h and t statistic as well). Does anyone know if any of these tests can be done in PROC AUTOREG as compared to having to go to PROC ARIMA to generate them?
If you are using PROC PDLREG how do you show lags of the dependent variable on the right side? I know how you do this for predictor (independent variables] but I don't know how to tell SAS to include lags of Y on the right side of the model.
There are a variety of ways to tell if the residuals are white noise, Box-Ljung and Breusch-Godfrey are the two I know of (I guess Durbin's h and t statistic as well). Does anyone know if any of these tests can be done in PROC AUTOREG as compared to having to go to PROC ARIMA to generate them?
If you are using PROC PDLREG how do you show lags of the dependent variable on the right side? I know how you do this for predictor (independent variables] but I don't know how to tell SAS to include lags of Y on the right side of the model.