Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: interpret results from conditional logit model


From   "Wei Tan" <tanwei@hotmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: interpret results from conditional logit model
Date   Tue, 03 Jun 2003 02:26:25 +0800

Hi,

I am sorry that my email account block the stata list last time. therefore I did not receive any reply from your list.

I am trying to use clogit to estimate McFadden's choice model. My question is how to interpret the results from Stata.

I will illustrate with the example in STATA Reference.

data:

id car choice dealer sex

1 american 0 18 male
1 Japan 0 8 male
1 Europe 1 5 male
2 American 1 17 female
2 Japen 0 6 female
2 Europe 0 2 female


if I use the following command:

gen Japan=(car==2)
gen europe=(car==3
gen sexJap= sex*japen
gen sexeuro=sex*europe
clogit choice japan erupe sexjap sexeur dealer,group(id)

I have two questions:

1. How should I interprete the estimated coefficient and odds ratio for japan and dealer

2. if I want to restrict sex to have the same effect for Japan and Europe car. how should I do?

thanks

_________________________________________________________________
The new MSN 8: advanced junk mail protection and 2 months FREE* http://join.msn.com/?page=features/junkmail

*
* 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/




© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index