Tulika Narayan wrote:
> I plan to estimate an occupational choice model with job characeteristics
> (clogit) with data that have multiple observations on the same individuals.
> To control for the fact the observations are not independent, I planned to
> use the cluster option. However, this is not specified in clogit (or nlogit
> that I may use). Any suggestions? Is this related to how the data is set up
> for clogit wherein there are multiple rows for each individual depending on
> how many choices there are.
and Clive Nicholas <[email protected]> responded:
> You must be looking at a completely different version of -clogit- than are
> the rest of us. Pop along to -whelp clogit-, where you will find that
> -cluster- is indeed an option.
Tulika need only update his Stata first. These options were added after
Stata 8 was released.
--Bobby
[email protected]
*
* 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/
