st: RE: RE: RE: AW: interactions for xtmelogit models

["Hardy, Dale S" <Dale.S.Hardy@uth.tmc.edu>]

My reservations are from basic principles I learned in logistic regression class...that the models with interaction terms must be hierarchically well-formed to give correct estimates.

Both the single term (age) and the interaction term with age must be in the model.

Is it different with xtmelogit models? And why?


I just want to clarify this before I run the model.


Thanking you in advance.




Dale Hardy, PhD RD CDE CHES
Research Associate
University of Texas School of Public Health
Houston, TX 77030
Phone: (713) 500-9221
Fax: (713) 500-9264
Email: dale.s.hardy@uth.tmc.edu



________________________________________
From: owner-statalist@hsphsun2.harvard.edu [owner-statalist@hsphsun2.harvard.edu] On Behalf Of Martin Weiss [martin.weiss1@gmx.de]
Sent: Monday, February 22, 2010 11:14 AM
To: statalist@hsphsun2.harvard.edu
Subject: st: RE: RE: AW: interactions for xtmelogit models

<>

" Why isn't age not in the model? Age is with the interaction terms but not
as a single term. Would that make the model not hierarchally well-formed?  "



The answer is probably that the intention is "... to test against a model
with no gender interactions, fixed or random", as stated at the bottom of
page 14 of http://www.stata.com/meeting/fnasug08/gutierrez.pdf. So the focus
is on interactions, not the main effect.



HTH
Martin


-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Hardy, Dale S
Sent: Montag, 22. Februar 2010 17:59
To: statalist@hsphsun2.harvard.edu
Subject: st: RE: AW: interactions for xtmelogit models

Hi Martin,

A few months age I asked you a question about xemelogit interaction and you
send me the link below.


On page 15/36 of the presentation by Gutierrez entitled, ‘Tricks of the
trade: getting the most out of xtmixed’,  is a model for xtmixed
interaction.

My question is:
Why isn't age not in the model? Age is with the interaction terms but not as
a single term. Would that make the model not hierarchally well-formed?


Thanks in advance for clarifying this issue.



I look forward to hearing from you.


Dale



Dale Hardy, PhD RD CDE CHES
Research Associate
University of Texas School of Public Health
Houston, TX 77030
Phone: (713) 500-9221
Fax: (713) 500-9264
Email: dale.s.hardy@uth.tmc.edu



________________________________________
From: owner-statalist@hsphsun2.harvard.edu
[owner-statalist@hsphsun2.harvard.edu] On Behalf Of Martin Weiss
[martin.weiss1@gmx.de]
Sent: Friday, October 16, 2009 9:38 AM
To: statalist@hsphsun2.harvard.edu
Subject: st: AW: interactions for xtmelogit models

<>



Note, for instance, the heavy use of interaction terms in
http://www.stata.com/meeting/fnasug08/gutierrez.pdf, slide 15. The
presentation is about -xtmixed-, but it may still help you approach your
problem.

Also see http://www.stata.com/meeting/2sweden/gutierrez_sweden07.pdf for
-xtmelogit-



HTH
Martin


-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Hardy, Dale S
Gesendet: Freitag, 16. Oktober 2009 16:17
An: statalist@hsphsun2.harvard.edu
Betreff: st: interactions for xtmelogit models

Hi All,

I am looking at examples of xtmelogit models. I did not see any interaction
terms used or any mentioned that interaction terms is recommended for use in
these models.

Have any of you who use this method used interaction terms in your modeling?

How do you interpret the exposure variable with the interaction term/s and
the addition of mixed effects variables/s?


Any help is appreciated.


Thanks.




Dale

Dale Hardy, PhD RD CDE CHES
Research Associate
University of Texas School of Public Health
Houston, TX 77030
Phone: (713) 500-9221
Fax: (713) 500-9264
Email: dale.s.hardy@uth.tmc.edu




*
*   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/


*
*   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/