Statalist The Stata Listserver

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

Re: st: linear probability model vs. probit/logit

From   Richard Williams <>
Subject   Re: st: linear probability model vs. probit/logit
Date   Tue, 03 Oct 2006 16:26:20 -0500

At 03:04 PM 10/3/2006, Nishant Dass wrote:
Hi Maarten,
Thanks for the link.  I read it but I wonder - does perfect
prediction result in exclusion of those observations?
Yes, but you should be getting a warning message about cases being dropped if that is what is happening. In addition, you said you had 12,000 case for logit/probit and 10,000 for ols. Unless you had that backwards, that would not be consistent with cases being dropped because of perfect prediction, i.e. the N for logit/probit should be smaller than the N for ols if perfect prediction is costing you cases.

Hi Richard,
I checked again and my runs aren't different.  I simply
replaced the -reg- with -logit- and re-run the command, and
get a different no. of obs.  I am not sure how useful would
pasting my command be for you because there's really
nothing different between the two commands that I am
running (except the estimation method.)
Is there anything else involved, like weights or clustering?

Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX: (574)288-4373
HOME: (574)289-5227
EMAIL: Richard.A.Williams.5@ND.Edu
WWW (personal):
WWW (department):
* For searches and help try:

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