Hi there.
I am running a panel data model using Stata's xtreg command.
Some texts (e.g. Wooldrigde) frequently include time dummies (or in
Stata language indicator variables)in applications.
I get good results before including a complete set of time dummies,
but if I include the dummy for one particular year, the last one in
the panel, the results change dramatically! Only a couple of the
dummies are significant (T=5 N=60). Must I include them? Any
recommendations? What is happening here? Any remark regarding common
practice with dummies in panel data? Bibliography?
Many thanks
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
