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

Re: st: quasi-variances in Stata

From   Daniel Stegmueller <>
Subject   Re: st: quasi-variances in Stata
Date   Fri, 9 May 2008 18:13:52 +0200


two (technical / nontechnical) references would be:

Firth, D. & De Menezes, R. X.
Biometrika, 2004, 91, 65-80

Gayle, V. & Lambert, P. S.
Using Quasi-variance to Communicate Sociological Results from Statistical Models
Sociology, 2007, 41, 1191-1208


Am May 9, 2008 um 3:47 PM schrieb Richard Goldstein:

I am not familiar with either Firth or Fox (2008) (note that the FAQ asks for complete references); nor am I familiar with the term "quasi-variances";

Why not just use the test statement after your regression to test exactly the comparison you want?


Thomas W. Volscho wrote:

Does anyone know if Stata has plans to (or has already) incorporated a native routine to obtain quasi-variances for testing differences between dummy variables and not just differences b/w each dummy and reference category?
Firth has done work in this area and it is outlined in John Fox's new (2008) applied regression text.
*   For searches and help try:
Daniel Stegmueller
Landgrafenstr. 14, App.45
60486 Frankfurt a.M.

*   For searches and help try:

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