[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: reporting beta coefficients in GEE

From   Maarten buis <>
Subject   Re: st: reporting beta coefficients in GEE
Date   Mon, 3 Aug 2009 02:23:03 +0000 (GMT)

--- On Sun, 2/8/09, Alison McCarthy wrote:
> I was wondering whether there was a problem if I reported
> standardised coefficients? I have many variables that are
> scaled differently and do not appear to be comparable in the
> using the usual b scores. I am using GEE, pa f(nb)
> corr(exch)

In principle there is nothing wrong with standardizing 
variables to make their coefficients comparable. I'd be a bit 
hesitant to compare the effects of variables that are very 
different on substantive reasons. I'd rather report the 
effect of getting a year older and getting a euro/dollar more 
income on a dependent variable. Standardizing means that you 
loose these substantively interesting metrics, which is often 
more important to me than finding the "strongest" effect.

Hope this helps,

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen


*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index