At 04:00 PM 5/8/2009, Jason Dean, Mr wrote:
Hmm, I'll have to take a look at it again. But when I run separate
ologits and do predicted values they are much different then when I
combine the sample and include a immigrant dummy (and of course
interact all covariates). Maybe I made a typo in my code.
You are only allowing for index shift (all cutpoints differ by the
same amount) by doing so, so your pooled model is more constrained
than when you run separate ologits. If you want a pooled model to
perfectly reproduce your separate ologit results, try something like
use "http://www.indiana.edu/~jslsoc/stata/spex_data/ordwarm2.dta", clear
ologit warm yr89 if male, nolog
ologit warm yr89 if !male, nolog
gen maleyr89 = male * yr89
gologit2 warm yr89 male maleyr89, npl(male) lrf
The code I gave earlier would be handy if you thought the only
difference between groups was in their cut points.
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/