Better, you may just have a look at the statistics menu in your copy of the software. About in the middle, you will find the submenu longitudinal/panel data (at least, this is what I find on Intercooled Stata 9 for windows). A minimum knowledge of statistics should point you to linear models, and then a minimum imagination should tell you what FE, RE, PA, FD mean (otherwise, you may just open the next command window).
Nicola
At 02.33 14/10/2007 -0400:
>Date: Sat, 13 Oct 2007 20:35:05 +0200
>From: Justina Fischer <[email protected]>
>Subject: Antwort: st: commands for random effects for continuous data
>
>- --0__=4EBBF9E0DFF590468f9e8a93df938690918c4EBBF9E0DFF59046
>Content-type: text/plain; charset=US-ASCII
>
>... why don't you engage in searching the Stata archives and net sources
>using -search- (e.g. for 'random effects model') and pose your question
>only in case you really cannot find an answer ?
>
>Justina
>
>
>Dr. Justina A.V. Fischer, M.A.
>University of St. Gallen
>CH-9000 St. Gallen
>
>- [email protected] schrieb: -----
>
>I always feel the need to apologise for asking basic questions!
>Anyway here goes:
>
>I've been using a population averaged approach to predicting continuous
>outcomes in panel data (XTGEE), but I am now considering using a random
>effects model, as the assumptions about the differences between panels
>are less generalised.
>
>Which commands are available in stata to deal with random effects for
>continuous data? Xtmixed? Gllamm? Will I have to specify a correlation
>structure as in xtgee?
>
>
>Cheers
>
>Seyi
>
>
>Seyi Soremekun
>PhD Student
>Biological Sciences Department
>University of Warwick CV4 7AL
>+44 02476522473
*
* 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/
