Re: st: sorry for HTML email: compare raw or marginal effects

[Richard Williams <Richard.A.Williams.5@ND.edu>]

At 05:13 AM 5/9/2007, Dirk Nachbar wrote:
> I have one logit model for two subgroups, I want to compare if the 
> confidence intervals for the coefficients across regressions overlap 
> (to see if they could be the same), should I use intervals for raw 
> coefficients or marginal effects?
There are assorted problems with trying to make such group comparisons.  See

http://www.indiana.edu/~jslsoc/files/talks/long-nd-2007-04-16.pdf

http://www.nd.edu/~rwilliam/oglm/RW_Hetero_Choice.pdf

http://www.business.uiuc.edu/ghoetker/documents/Hoetker_comp_logit.pdf

I definitely wouldn't use the confidence intervals for the 
coefficients; marginal effects I am not sure about.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW:    http://www.nd.edu/~rwilliam

*
*   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/