Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Mayson Brian" <zerama@myself.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st:panel unit specific intercepts |
Date | Fri, 20 Apr 2012 06:55:47 -0400 |
Dear All, I have been estimating the panel data model yit=xit`b+uit+eit My data consists of 14 panel units and 29 time periods. After the estimation, when I see the residuals the sum of the residuals is zero only when the fitted value is taken with the effect i.e., using the post estimation command: predict xb, xbu, which includes the within group effects. I can see also that each unit has different value for ui, and hence each panel unit has its own unit specific intercept. My question is that is there a method to tell stata estimate average intercept for the panel units not just unit specific intercepts. Even the unit specific intercepts are not straight forward, I can only see that after predicting the ui that each panel unit has to have a different intercept. Any suggestion to deal with this problem. Many thanks for your help Mayson * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/