Robust Hausman test for FE vs RE

For quite a while I was writing a program to perform a Hausman test to compare Fixed vs Random Effects in Stata when the estimates were calculated using cluster-robust standard errors, since in this case the usual Hausman test is not suitable. Just when I was about to finish with it, I found out that there is already a user-written program that does this and several other tests that fall into the “overidentifying restrictions” class for panel models. The command name is xtoverid and it can be very useful, especially if you are using panel IV methods or Hausman-Taylor models.


Leave a Reply