Many thanks. It turns out that the procedure is different for
discrete outcomes (see section V in the article). Does anyone have
code for that? Here is the full citation for the Clogg et al. article:
Clogg, Clifford C., Eva Petkova, and Adamantios
Haritou. 1995. Statistical Methods for Comparing Regression
Coefficients between Models. American Journal of Sociology 100:1261-93.
Rob
At 03:06 AM 5/30/2006, you wrote:
--- Rob Baller wrote:
> I would like to compare coefficients, on the same independent
> variable, between two nested models. For example, I want to
know if the b2
> coefficients shown below are significantly different from each other:
>
> y = b1x1 + b2x2
> y = b1x1 + b2x2 + b3x3
>
> The routines described by Clogg, Petkova, and Haritou (1995) AJS
are what I
> want to implement.
Rob:
I am not familiar with this method, but a quick look at the
article shows that their method uses only quantities that
-regress- returns after you estimate a model, so you can
easily do it yourself, like the example below:
HTH,
Maarten
*---------- begin example ----------
sysuse auto, clear
reg price mpg
scalar b = _b[mpg]
scalar vb = _se[mpg]^2
scalar ve = e(rmse)^2
reg price mpg foreign
scalar d = scalar(b)-_b[mpg]
scalar se = sqrt(_se[mpg]^2-scalar(vb)*e(rmse)^2/scalar(ve))
di scalar(d)
di scalar(se)
*------------ end example -----------
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting adress:
Buitenveldertselaan 3 (Metropolitan), room Z214
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
*
* 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/
*
* 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/