Im working on panel regression for school, using 45 cross-sectional (countries) over a 3 year period ('05,'10,'15), 118 observations and 5 independent variables (including const).

When running the regression on gretl, I found the durbin-watson equal to 1.817, meaning there is positive autocorrelation right?

But when I looked up the critical values (dl=1.63029;du=1.78873), I found the durbin-watson is greater than 'du'. Does this mean there is no autocorrelation? If there is autocorrelation, how can I fix my model to prevent autocorrelation?

Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.