Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: st: Odds ratio
From
"Martin Weiss" <[email protected]>
To
<[email protected]>
Subject
RE: st: Odds ratio
Date
Fri, 9 Apr 2010 23:19:55 +0200
<>
"Do you know if Stata allows us to use -xtmelogit- and -gllamm-, which are
appropriate for multilevel binary dependent variable analyses, together with
prediction of probabilities using -predict- command?"
You should just take a look at -help gllapred- and -help xtmelogit
postestimation-.
HTH
Martin
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Rosie Chen
Sent: Freitag, 9. April 2010 22:27
To: [email protected]
Subject: Re: st: Odds ratio
Thank you all for the very informative discussions on odds ratio and
predicted probability. Very useful. May I ask one more question? Do you know
if Stata allows us to use -xtmelogit- and -gllamm-, which are appropriate
for multilevel binary dependent variable analyses, together with prediction
of probabilities using -predict- command?
Rosie
----- Original Message ----
From: Richard Williams <[email protected]>
To: "[email protected]" <[email protected]>;
"[email protected]" <[email protected]>
Sent: Fri, April 9, 2010 3:58:15 PM
Subject: Re: st: Odds ratio
At 07:47 AM 4/9/2010, Maarten buis wrote:
>I always think of it as a "smart" way of adding a dummy for
>each group. For example when you look at persons nested
>in schools, this would be a way of adding school dummies.
>The whole point of doing random effects models is that we
>put some additional constraints on these dummies, e.g.
>not correlated with any of the observed variables, etc,
>but that is not relevant for this case. The problem with
>getting predicted probabilities is that we don't directly
>estimate these dummies, so we miss a key set of variables
>and coefficients that are necesary for computing the
>predicted probabilities.
A "trick" used by Long & Freese's SPOST commands is to generate
temporary fake cases with the desired X values, and then use the
predict command to get the predicted probabilities. Would this work
with an HLM model estimated with Stata? Of course, even if it did,
maybe it would be extremely unwieldy because we would want to
generate fake cases for every group.
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/