I have a question regarding Panel data modeling. We are estimating a model with Panel OLS (no fixed or random effects) and found that there are no tests for the regular assumptions related to OLS. We decided to eliminate the panel structure to be able to run these tests. Is that the correct way of doing this?
The other question is regarding the GLS estimator. We found that there are both heteroskedasticity and autocorrelation in our series. We decided to correct these problems using GLS. How should we decide between period and cross section weights?
Thank you!
Panel data GLS weight options
Moderators: EViews Gareth, EViews Moderator
Who is online
Users browsing this forum: No registered users and 39 guests