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

Re: st: No constant with XTMELOGIT

From   "Susan Mason" <[email protected]>
To   <[email protected]>
Subject   Re: st: No constant with XTMELOGIT
Date   Mon, 28 Jan 2008 17:09:41 -0700

Thank you for the clarification.  

>>> Maarten buis <[email protected]> 1/28/2008 2:39 PM >>>
--- Susan Mason <[email protected]> wrote:
> First, I did wonder if using OR was causing my problem but decided
> must be something else because the examples in the Stata manual show
> a constant when using OR. 

If you look at example 4 on page 236 you will see that -xtmelogit-
not show the constant with the -or- option.

> I agree this is an important statistic. Please correct me if I am
> wrong, but when I report my results this constant would represent
> grand mean of model, correct? 

It is the baseline odds, so the number of persons experiencing a
success for every person experiencing a failure, if all explanatory
variables are equal to zero and the random effects take on their
average value. I use the term success to denote the value 1 for your
dependent variable and failure to denote the value 0. You should
replace the words success and failure with other terms that suit your

> I guess one way around this is to run it without OR and then report
> both statistics with an asterisk explaining the grand mean is not
> generated when using odds ratios.  Would this be acceptable?

That would be unnecesary and confusing for your reader. In my previous
post I showed you how to compute this baseline odds. Add those to your
table at the place where you would expect the constant. There is no
need to mention that you took any special action in attaining them.
did not change an estimation method, you only changed the way the
results are presented. Those who would understand such a comment would
know it anyhow, all others will only get confussed by such comments.

I think all other question are already answered by Jay.

Hope this helps,

Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715 

Sent from Yahoo! Mail - a smarter inbox 

*   For searches and help try:
*   For searches and help try:

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