11. Hausman Test using EViews || Dr. Dhaval Maheta

[@mohammedyounus8632]

Thanks and regards

[@mohammadkashem3375]

Dear Sir, I rely on E-views software for Panel data estimation process. I have a question to you. Please answer me. When I conduct the Huasman test, the "Chi-square Statistic" is significant when I choose "Random Effect" for "Cross Section" during the effect specification. As you know it is meaning that FIXED EFFECT model is correct in this case. However, the "Chi-square statistic" is insignificant when I choose the "Random Effect" for "Period" for conducting the Hausman test. As you know it means that RANDOM EFFECT model is correct model in this case. Which model should I choose for estimation in this situation? "Random Effect" or "Fixed Effect" model?

[@mohammadkashem3375]

Hi Sir, if Hausman test indicates that fixed model is more appropriate than random effect model, and if in that case, in data time period (T) > cross section units (N), which FEM is to be chosen: time (T) FEM or Cross section (N) FEM?

[@ZAKARIAEMAJID]

Sir, I think you made a mistake, because you said that the p-value is more than 5% which means that we accept the null hypothesis and not the contrary, then the random effect is appropriate

[@DhavalSaifaleeAaryash]

we dont write accept the null, technically we write "fail to reject null" which means same thing

[@ZAKARIAEMAJID]

@@DhavalSaifaleeAaryash Yes, you are absolutely right, I forgot that, thank you sir,