Correlation in Residuals

[ancraeg52]

Hi,

I am running a simple LS model with (-1) AND (+1) of the dependent variable as well as other explanatory variables. However i get a very low DW Stat and have been told that one solution is to treat the residual as an unknown but important omitted variable and then put the residual variable into the equation. Does any one have an idea on how to perform this on Eviews?

Thanks a lot.
Julian

[startz]

You have been misadvised.

To see why, try

Code: Select all

ls y c x series e = resid ls y c x e

and look carefully at the results of the last regression.