Despite reading some statistics manual and original papers I am still not sure to have understood correctly the use and the alternative hypotheses for several tests to be used after -xtreg-.
Command -xttest0- is referred to as "the Breusch and Pagan Lagrange-multiplier test for random effects, a test that Var(v_i)=0". I argue that if the test is significant, the model is better estimated through -regress-. Am I right?
There are several user-written tests (namely, -xttest1-, -xttest2-, -xtcsd-) and don't forget the built-in F test that all u_i=0 (automatically reported below the estimates for fixed effect models), which, while working after different specifications of -xtreg- (some require the random effects, some the fixed effects, some that the panel is balance, etc...), seem to perform the same job, i.e. help me to choose between -xtreg- (if the test is not significant) and -regress- (if the test is significant). Am I right again?
Finally, it is only -hausman- that helps me to choose between fixed (if the test is significant) and random effects (if the test is not significant), isn't it? Is there any test to choose between random effect and population-averaged?
Thanks,
Nicola
*
* 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/
