Regression with correlated erros

[Anuashla]

I am trying to predict warranty contract sales using vehicles sales volume as the dependent variable. I ran a simple regression model but there is a time series pattern that I noticed in the residuals. Proc Autoreg did seem to be a solution to this modeling problem but then in autoreg, dependent variable is time itself whereas in my model exogenous variable is vehicles volume and the residuals are time dependent. Is there any way I can fix this issue?

Thanks

[udo_sas]

Hello -

Did you have a chance to look at: http://support.sas.com/documentation/cdl/en/etsug/68148/HTML/default/viewer.htm#etsug_arima_gettings... as a starting point?

Thanks,

Udo