I have a question when I apply fixed and random model, then hausman test, the results show that the appropriate one is fixed model based on hausman test, then I want to check the heterocedasticity for the fixed model using xttest3 (modified wald test ) I found that there is an heteroscedasticity to correct it I have added option robust with fixed. Is it sufficient or then I have apply once again hausman, because I already try it I get this message hausman cannot be used with vce(robust) ... Also I have another question is it sufficient to decide between re and fixed model using hausman, can we use for example R2


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.