Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: re: panel re vs. fe model


From   [email protected]
To   [email protected]
Subject   st: re: panel re vs. fe model
Date   Fri, 19 Jan 2007 15:55:15 +0100

This thread is very interesting and I think it is an occasion to re-post two old questions that has not found an answer, yet, and to post a new - though related - one. Is there any test to choose between random effect and population-averaged? I guessed that one uses -xttest2- (or -xtcsd-) hoping to find a non-significant result: what should I do if the test is significant? 
If I cluster on panel ID variable, "intracluster correlation" sounds to me as pointing to correlation between observations with the same ID (autocorrelation). 
Which is the difference (i.e. how can I choose) between -xtgee- and any xt command clustering on the panel ID variable, if any?
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/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index