I executed a regression by using Eviews, the DW stats were about 0.25. It means the presence of serial correlation in errors. Could someone help me find a solution or how to correct it. Thank you in advance!
In the long run, we're all dead.
yeah, the DW too low is a sign of autocorrelation. what my suggestion is, you can run a timeseries analysis; but i do not know what exactly your problem is, so i can not suggest the method.
however, if your intention is to run a linear regression, i think you can still proceed with it. the low value of DW test says that there MAY BE an autocorrelation.
because this problem also arose in my study, i can clear a bit more if u can give me ur research question.
Advertise on Talk Stats