Adrian,

for discussing the magnitude you need to calculate marginal effects, which are not identical to coefficients in an order logit/probit model.


Justina


Dr. Justina A.V. Fischer, M.A.
University of St. Gallen
CH-9000 St. Gallen

[email protected] schrieb: -----

An: [email protected], <[email protected]>
Von: Richard Williams <[email protected]>
Gesendet von: [email protected]
Datum: 29.02.2008 05:03AM
Thema: Re: st: ordered logit (was: marginal effects in random effects  ordered probit using GLLAMM)

At 05:31 PM 2/28/2008, Adrian de la Garza wrote:
>Could anyone recommend a source that discusses how to interpret
>these coefficients? I have read a few papers in the "economics of
>happiness" literature where they use these ordered logits and
>probits but they never discuss what the magnitudes of the
>coefficients mean; they care only about the coefficients' signs and
>statistical significance. Similarly, the standard Greene
>econometrics textbook has very little regarding this interpretation.

Long and Freese's book is very good on this.  See

http://www.stata.com/bookstore/regmodcdvs.html

Even if you don't get the book, download their -spost9- routines,
which you can locate with -findit-.

If you want something quickly, the notes for my categorical data
analysis class are online at

http://www.nd.edu/~rwilliam/xsoc73994/index.html

See especially

http://www.nd.edu/~rwilliam/xsoc73994/L11.pdf

http://www.nd.edu/~rwilliam/xsoc73994/L12.pdf


-------------------------------------------
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/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/