Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: goodness-of-fit measure for svyprobit

From   "Sayer, Bryan" <>
To   "''" <>
Subject   st: RE: goodness-of-fit measure for svyprobit
Date   Wed, 16 Oct 2002 09:10:30 -0400

With survey models, logit has a pseudo-r^2, but even that is of little use,
other than to compare different models on the same data for a RELATIVE
goodness of fit.  About the best approach is a table of some type based on
predicted values.  See for example Korn, E. and Graubard B. "Analysis of
Health Surveys" pages 106-108.  Available in the Stata bookstore, I believe.

Bryan Sayer
Statistician, SSS Inc.

-----Original Message-----
From: joachim Wagner []
Sent: Wednesday, October 16, 2002 2:21 AM
Subject: st: goodness-of-fit measure for svyprobit

Dear All:

A referee asks for a goodness-of-fit measure for a model I estimated with 
svyprobit. Maybe because svyprobit is not a "true" ML estimator I cannot 
find such a number in the output. Although I do not see what we can learn 
from such a measure I do not want to struggle with the referee. Can 
somebody out there help me finding a solution? Many thanks in advance.


Prof. Dr. Joachim Wagner
University of Lueneburg
Institute of Economics
Campus 4.210
D-21332 Lueneburg
Phone: +49-4131-78-2330
Fax: +49-4131-78-2026

*   For searches and help try:
*   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