Statalist


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

st: AW: RE: cross-model hypothesis test


From   "Martin Weiss" <martin.weiss1@gmx.de>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: AW: RE: cross-model hypothesis test
Date   Mon, 23 Mar 2009 16:53:05 +0100

<> 

" Martin: Thanks again for telling me about the suest option"

 You are welcome and thanks for the flowers :-)



" I am not sure if it will work with the RE option". Just check:

*************
webuse nlswork, clear
generate age2 = age^2
generate ttl_exp2 = ttl_exp^2
generate tenure2 = tenure^2
generate byte black = race==2
xtset idcode

xtreg ln_w grade age* ttl_exp* tenure* not_smsa south if black, re
estimates store first
xtreg ln_w grade age* ttl_exp* tenure* not_smsa south if !black, re
estimates store second

suest first second
*************



HTH
Martin

-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Jason Dean, Mr
Gesendet: Montag, 23. März 2009 16:44
An: statalist@hsphsun2.harvard.edu
Betreff: st: RE: cross-model hypothesis test

I actually just used suest for an ordered logit model and it worked great.

I am not sure if it will work with the RE option, however, you can run each
model separetly (pooled OLS) and then use the VCE(cluster) option with
suest. This will give you the appropriate standard errors for pooling
individuals over time. 

Hope this helps..

Martin: Thanks again for telling me about the suest option

Jason



________________________________________
From: owner-statalist@hsphsun2.harvard.edu
[owner-statalist@hsphsun2.harvard.edu] On Behalf Of Joshua A Shindell
[shindell@uwm.edu]
Sent: Monday, March 23, 2009 11:29 AM
To: statalist@hsphsun2.harvard.edu
Subject: st: cross-model hypothesis test

Hello,

I am looking for a method to perform cross-model hypothesis tests of
regression coefficients.  I understand that the command "suest" is designed
for this purpose, but does not work when xtreg with the re option is the
estimation method used.

Thank you for any suggestions,

Joshua A. Shindell


*
*   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/



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