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

Re: st: SAS versus Stata, Panel Study Logit models

From   Richard Williams <[email protected]>
To   [email protected], "Statalist" <[email protected]>
Subject   Re: st: SAS versus Stata, Panel Study Logit models
Date   Wed, 19 Dec 2007 14:11:41 -0500

At 12:46 PM 12/19/2007, Joseph Coveney wrote:
Nevertheless, if there are only two categories for a given predictor, then
any SAS-versus-Stata difference would at worst only result in a change of a
coefficient's sign (inversion of the OR).  Are the numerical differences in
coefficients you're seeing with multiple (>2) categories?  If they're in
two-category predictors, are the small differences perhaps ones that are ca.
OR = 1, i.e., an OR of 0.98 in one package is 1.02 in the other?  Are the
differences observed in categorical-by-continuous-predictor interaction
First off, thanks to Joe and Phil and David and any others who have responded. She reports her coefficients to 3 decimal places. For logit the SAS and Stata results are the same for 3 decimal places. If you rounded to 2 decimal places the SAS and Stata GEE results would almost all be identical, at least for the coefficients. The standard errors differ a little more than that but the FAQs seem to explain why that is. She also has some race dummies in there where the reference category only has 2.7% of the cases, so that may be contributing to some collinearity issues.

Too bad I don't have SAS so I could fool around with it. At this point though, my inclination is to think that the small differences in coefficients just reflect rounding and the slightly larger differences in standard errors reflect differences in how they are computed.

Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]

* For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index