Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: logit fe with svy panel data.
From
[email protected] (Jeff Pitblado, StataCorp LP)
To
[email protected]
Subject
Re: st: logit fe with svy panel data.
Date
Tue, 20 Dec 2011 11:01:51 -0600
Sumedha Gupta <[email protected]> is trying to use -clogit- with the
-svy- prefix:
> I wish to use the HRS data to do an individual level panel fixed
> effects estimation for a binary outcome. xtlogit does not work since I
> only have pweights and also these are not constant across waves. svy
> command with clogit does not seem to work because if I run:
>
> svy subpop(pop1): clogit rdepres age age2, group(hhidpn)
>
> it gives me an error 'invalid vcetype
> r(198);
>
> I believe this is because clogit defines clusters at group level as
> opposed to individual level (not sure about this though). Is there are
> alternative I can use? I found a similar question posted earlier:
>
> http://www.stata.com/statalist/archive/2011-11/msg00325.html
>
> However I couldn't see the answer.
>
> Any help will be much appreciated.
It appears Sumedha forgot to put a comma between -svy- and the -subpop()-
option. The correct syntax is
. svy, subpop(pop1): clogit rdepres age age2, group(hhidpn)
In Sumedha's case, -clogit- requires that the levels of variable 'hhidpn' are
nested within the final stage sampling units. Also -clogit- requires that the
sampling weights are constant within the levels of 'hhidpn' variable.
--Jeff
[email protected]
*
* 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/