Statalist


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

st: RE: robust Hausman test, xtpcse


From   "Schaffer, Mark E" <M.E.Schaffer@hw.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: robust Hausman test, xtpcse
Date   Wed, 30 Sep 2009 16:01:40 +0100

Caroline,

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> Caroline Johanna Biehl
> Sent: Tuesday, September 29, 2009 10:34 AM
> To: statalist@hsphsun2.harvard.edu
> Subject: st: robust Hausman test, xtpcse
> 
> Hello!
> I am rather new to stata and so experiencing some problems 
> when analyzing my data. i want to do a hausman test but it 
> has to be robust and correct for autocorrelation. I found on 
> the list to use -xtoverid, which works with -xtreg, robust 
> and rejected RE. But does it also control for 
> autocorrelation?

If you call -xtoverid- with the cluster option, you will get an overid statistic that is robut to arbitrary within-panel heteroskedasticity and autocorrelation.

Cheers,
Mark

> I read that to use -xtpcse is appropriate 
> for AR1 and heteroscedasticity. Or is there a better option? 
> Unfortunatly, xtpcse does not work with option -,fe. What is 
> better to use then?
> 
> Thank you!
> Caroline
> 
> 
> 
> 
> Here some results:
>  quietly xtreg   avcons over65perc averagesize backlogper li 
> mp  formalpercent  totalincome  avp, re robust
> 
> . xtoverid
> 
> Test of overidentifying restrictions: fixed vs random effects
> Cross-section time-series model: xtreg re robust 
> Sargan-Hansen statistic  42.990  Chi-sq(5)    P-value = 0.0000
> 
> 
> . xtpcse   avcons over65perc averagesize backlogper li mp  
> formalpercent  totalincomeavp, corr(ar1)
> (note: estimates of rho outside [-1,1] bounded to be in the 
> range [-1,1])
> 
> Prais-Winsten regression, correlated panels corrected 
> standard errors (PCSEs)
> 
> Group variable:   id                            Number of obs 
>      =       164
> Time variable:    expenditure                   Number of 
> groups   =        41
> Panels:           correlated (balanced)         Obs per 
> group: min =         4
> Autocorrelation:  common AR(1)                                
>  avg =         4
>                                                               
>  max =         4
> Estimated covariances      =       861          R-squared     
>      =    0.5733
> Estimated autocorrelations =         1          Wald chi2(8)  
>      =  40946.47
> Estimated coefficients     =         9          Prob > chi2   
>      =    0.0000
> 
> --------------------------------------------------------------
> ----------------
>              |           Panel-corrected
> avconsserv~u |      Coef.   Std. Err.      z    P>|z|     
> [95% Conf. Interval]
> -------------+------------------------------------------------
> ----------------
> over65perc~t |  -24.60873   15.55986    -1.58   0.114    
> -55.10549    5.888026
>  averagesize |   22.83173    17.0991     1.34   0.182    
> -10.68188    56.34535
>  backlogperc |  -4.946898   1.223853    -4.04   0.000    
> -7.345606    -2.54819
>      li      |   38.33405   37.61671     1.02   0.308    
> -35.39334    112.0614
>   mp         |  -43.72647   24.84609    -1.76   0.078    
> -92.42392    4.970983
> formalperc~t |   620.8446   284.6725     2.18   0.029     
> 62.89676    1178.792
> totalincome  |    .000799   .0000994     8.04   0.000     
> .0006042    .0009939
> avp |  -2.652616   .5862434    -4.52   0.000    -3.801632     -1.5036
>        _cons |   54.06299   103.0665     0.52   0.600    
> -147.9436    256.0696
> -------------+------------------------------------------------
> ----------------
>          rho |   .6798519
> --------------------------------------------------------------
> ----------------
> 
> -- 
> GRATIS für alle GMX-Mitglieder: Die maxdome Movie-FLAT!
> Jetzt freischalten unter http://portal.gmx.net/de/go/maxdome01
> *
> *   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/
> 


-- 
Heriot-Watt University is a Scottish charity
registered under charity number SC000278.


*
*   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