Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Controll for unobserved heterogenity in panel data


From   frauke.ruether@unisg.ch
To   statalist@hsphsun2.harvard.edu
Subject   st: Controll for unobserved heterogenity in panel data
Date   Sat, 31 Oct 2009 16:45:15 +0100

Dear Stata-list

I'm using a large unbalanced panel dataset to estimates effects of 
different factors on the patents probabilty to be granted. That means my 
dependent variable is a binary variable and there is, except from the 
dependent variable, not much variation over time.

I use xtlogit models and xtgee models. Because several patents are 
examined by the same examiner or applied by the same applicant we assume 
that the data contain cluster effects. 

The option cluster(.) is not allowed in xtlogit and xtgee models. Does 
anyone could give me a hint how I could controll for cluster effects?

Thank you for your help.

Best regards
Frauke
___________________________________


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index