Statalist


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

Re: st: xtlogit with panel variable


From   Jeph Herrin <junk@spandrel.net>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: xtlogit with panel variable
Date   Wed, 12 Nov 2008 10:18:38 -0500

The syntax for -xtlogit- has changed slightly. You can
still use the -i()- option, but it is deprecated and hence
not documented. Instead use

. xtset mycatvar

before running -xtlogit-. If you don't specify a panel
variable, I think -xtlogit- will return an error message.

Hope this helps,
Jeph


Fardad Zand wrote:
Hi Stataers,

I would like to run xtlogit, fe to resemble the method discussed in
Chamberlain (1980) "Analysis of Covariance with Qualitative Data" to
avoid several separate dummy variables for each category of data (you
can think of country-sector pairs). I believe I can do that by adding
the i() variable pointing to my category variable (here, the
country-sector pairs), RIGHT? What if I don't include the i() suffix
after xtlogit, fe?

Besides, I couldn't find i() among the options of xtlogit when looked
at the help while!!!!

Thank you so much for clarifying the issue to me.

Regards,
Fardad

*
*   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