Dear Statalist,
I have a question regarding joint F tests for a panel data. Stata gives me
different F tests if I add/drop cluster(ID) option.I wonder which one is
correct. Does it vary to which model I use, OLS, ordered probit, logit?
Appreciate your suggesion.
The following is my example:
The panel dataset contains 50 firms over 10 years. I run the following
regression:
"
regress Y X1 x2 x3 x4, cluster(firmID)
test x2 x3
"
Stata gives me result for F(2,49).
Is that the wrong joint F test?
If I drop cluster() option and run the above regression and tests, stata
gives me F(2,495).
Is that the right one?
I tried ordered probit model for the panel data, stats gives me different
chi2(2) with or without cluster() added.
Thank you,
Alice Sun
*
* 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/
