[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: probit vs. reg postestimation

From   "Martin Weiss" <>
To   <>
Subject   RE: st: probit vs. reg postestimation
Date   Sun, 24 Aug 2008 23:03:43 +0200

Also see Long and Freese (2006), chapter 4.4., for a discussion of residuals
in such models.


J. Scott Long and Jeremy Freese, Regression Models for Categorical Dependent
Variables Using Stata, 2nd Edition, Stata Press, 2006

-----Original Message-----
[] On Behalf Of Maarten buis
Sent: Sunday, August 24, 2008 10:51 PM
Subject: Re: st: probit vs. reg postestimation

--- Nirina F <> wrote:
> My dependent variable is a binary variable. Onn the following example
> y=b1x1+b2x2+b3x3+e,
> if I use reg to estimate b's , I should get more or less the same
> results as the marginal effects after probit.
> Now after reg, I can use predict e1, resid but after probit how can I
> get the same thing as e1?

There is no longer one type of residual after a model like -probit-,
but many different types, six of which are directly available after
-glm-, but only one after -probit-:

*--------------- begin example ----------------------
sysuse auto, clear
probit foreign price mpg
predict dev_probit, deviance

glm foreign price mpg, family(binomial) link(probit)
predict dev_glm, deviance
predict ans_glm, anscombe
predict lik_glm, likelihood
predict pea_glm, pearson
predict res_glm, response
predict wor_glm, working
*---------------- end example ------------------------
(For more on how to use examples I sent to the Statalist, see )

Hope this helps,

Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

Send instant messages to your online friends 
*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index