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

RE: st: Predicted value and dummy explantory variables


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: Predicted value and dummy explantory variables
Date   Tue, 15 Mar 2005 10:15:07 -0000

Clive's argument can be turned back on 
himself. Almost no variable ever actually 
has its own mean as a value. I can imagine 
situations in which averaging over dummies 
is acceptable as part of averaging over a  
set of predictors. It may not be orthodox, 
but I don't think it's always crazy. 

Nick 
n.j.cox@durham.ac.uk 

Clive Nicholas

> Dawat Lidia wrote:
> 
> > I am estimating OLS regression model. From this I was 
> trying to estimate
> > the
> > predicted value holding regressors at their mean value. But 
> I am not clear
> > if I can also hold dummy regressors at their means value. Is it
> > justifiable
> > to put dummy explantory variables at their mean value and obtain the
> > predicted value ?
> 
> No, it isn't: how can it be? If your dummy variable is 
> gender, how can it
> possibly make sense to estimate the effect of being 0.47 of a male on
> whatever the response of interest is?
> 
> A quick solution to your problem is to pop along to -whelp 
> adjust-. There
> you'll find that you can hold your continuous predictor and covariate
> variables at their means (if you desire), whilst setting your 
> dummies at 0
> or 1 (or both, if you choose to -adjust- twice).
> 

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index