Re: st: Re: clogit or logistic for matched pairs

[Michael Ingre <Michael.Ingre@ipm.ki.se>]

Thank You all

> gene byte baseline=1
> glm dv iv baseline, link(log) family(binomial) cluster(twinpairid) 
> eform noconst
Roger Newson pointed me in the right direction. I think RR is what I 
want together with the risk for  unexposed twins (or baseline). I 
noticed that RR also can be computed by -mcc- with data in the wide 
format (CI:s differs slightly though).

. mcc exposure_case exposure_control

And thank you Paul Visintainer and Jay Kaufman for showing me 
alternative approaches. It appears that the -xtlogit- solution is very 
close to -logit- except the robust variances. And -xtlogit- will 
reproduce the results of -clogit- if specified:

xtlogit dv iv ,i(pairid) fe or

Now it's way past bedtime. I will sleep on the matter, and probably 
dream about ratios and standard errors .

Thank you again.

Michael Ingre

-----------------
PhD-student
Department of Psychology
Stockholm University &
National Institute for
Psychoscial Medicine

*
*   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/