Xiaoqiang Cheng:
no, if you use -glm- to estimate a fractional logit the effect should
be interpreted in pretty much the same way as logit results, i.e. the
coefficents are the effects of the explanatory variables on the
"logit-transformed" proportions. You can get the effects on the
proportion using -mfx, predict(mu)-. I've given a presentation on
analysing proportions with Stata at the last London Stata User's
meeting. You can get the slides from
http://ideas.repec.org/s/boc/usug06.html and my website
http://home.fsw.vu.nl/m.buis/ .
HTH,
Maarten
--- "Cheng, Xiaoqiang" <[email protected]> wrote:
> BTW, since "glm" estimates likelihood, should we then interpret the
> coefficients of regressors as probability?
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting adress:
Buitenveldertselaan 3 (Metropolitan), room Z434
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
___________________________________________________________
NEW Yahoo! Cars - sell your car and browse thousands of new and used cars online! http://uk.cars.yahoo.com/
*
* 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/
