Re: st:glm with bin family and link probit VS. probit

[Richard Williams <richardwilliams.ndu@gmail.com>]

At 06:53 PM 5/31/2011, Judy You wrote:
> Dear Richard:
>
> Thanks for your replying my question and your trusting probit over glm
> in this case.
>
> The reason that i run the two models is to check if they got the same
> answer, as most of reference books said so. Now, we could see the
> difference. The difference is even bigger when the marginal effect is
> estimated after the modellings. Could any other experts explain if the
> glm program could be improved?

Most of the time you will get the same results with glm and probit, e.g.

sysuse auto
probit foreign weight mpg
glm foreign weight mpg, link(probit) family(binomial)

You just happened to pick a problematic example because failure was 
predicted perfectly in some cases. -probit- apparently has the 
specialized code to deal with such cases while the jack of all trades 
-glm- does not. Also, keep in mind that your -glm- run never 
converged while -probit- did, which may further contribute to the 
seeming differences between the two.

In general, if you have a choice between glm and a more specialized 
program, you will usually want the specialist. The code will run more 
quickly, the post-estimation commands will be more appropriate and 
diverse, and the error-checking may be better.

I suppose a programmer could try to improve -glm-, but that could 
also make it more bloated, and may not really be worth it given that 
you already have -probit-.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
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/