Any suggestions as to how I can include two different fixed effects with
xtreg and xtlogit (or areg and clogit)?
That is, I have data on households with several children at multiple
points in time, so I would like to control for unobservables specific to a
child that do not vary over time as well as unobservables specific to a
household in a given year that do not vary across children in that
household. Generating dummy variables for either would be very memory
intensive with this dataset (and biased for logit).
A related question: why does clogit no longer have a cluster option? Any
suggestions for how to cluster with clogit or xtlogit?
Thanks very much!
- dave
*
* 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/
