Statalist


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

st: AW: AW: interpreting distribution of theta in xtreg ,re theta


From   "Martin Weiss" <martin.weiss1@gmx.de>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: AW: AW: interpreting distribution of theta in xtreg ,re theta
Date   Tue, 7 Apr 2009 10:48:37 +0200

<> 

Sorry, you said you have Stata 8, so it should be -uniform()-, not
-runiform()-




HTH
Martin


-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Martin Weiss
Gesendet: Dienstag, 7. April 2009 10:42
An: statalist@hsphsun2.harvard.edu
Betreff: st: AW: interpreting distribution of theta in xtreg ,re theta


<> 

Well, note in this example from Baum(2006),
http://www.stata-press.com/books/imeus.html,
theta is a constant with a "complete" panel, i.e. every unit is observed
over all time periods. Run -xtdes- to see that.

When you drop single observations randomly, you get a distribution for
-theta- as the participation pattern in the panel is now no longer
homogeneous...


*************
*get data
use http://www.stata-press.com/data/imeus/traffic, clear

*regression with "complete" panel
xtreg fatal beertax spircons unrate perincK, re the
xtdes

*make it incomplete
drop if runiform()<0.1
xtreg fatal beertax spircons unrate perincK, re the
xtdes
*************



HTH
Martin


-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von
JOrsag@access.uzh.ch
Gesendet: Dienstag, 7. April 2009 10:23
An: statalist@hsphsun2.harvard.edu
Betreff: st: interpreting distribution of theta in xtreg ,re theta

Hello everybody,

Can somebody please help me with the following rather beginner problem of 
mine. Using STATA 8 I have computed couple of Regressions estimating Random 
effects usng xtreg ..., re theta which delivers the distribution of theta as

well. From the STATA Manual I have understood that theta is an important 
component in estimating random effects, but I am not sure how to interpret 
the distribution in other words what is the optimal distribution and are 
there some distributions which could question the whole regression result?


Thank you in advance for any comments and insight.

Greetings,

Jakub Orsag
*
*   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