Statalist


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

st: RE: Instrumental variables


From   "Schaffer, Mark E" <M.E.Schaffer@hw.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Instrumental variables
Date   Fri, 11 Sep 2009 11:49:24 +0100

Philio,

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> Philomela@gmx.net
> Sent: Friday, September 11, 2009 11:13 AM
> To: statalist@hsphsun2.harvard.edu
> Subject: st: Instrumental variables
> 
> Dear all,
> i habe a panel data set. One variable was suspected to be 
> endogenous and this was proven by Davidson and macKinnon test 
> and a hausman test of endogeneity. Therefore I used 
> instrumental variables. Random effects specification was 
> preferred by hausman test.
> 
> Now my questions:
> 1. I used dmexogxt for the Davidson and macKinnon test and 
> xtivreg2 for Anderson and Sargan test of validity of the 
> instruments, but both work only for fixed effects. Are there 
> commands for random effects too? Or can infer from them also 
> for the random effects model?

You should get rid of -dmexogxt- and switch to -xtoverid-.  It supports overidentification tests after random effects estimation with -xtivreg- and -xtreg-.

--Mark

> 2. I tested for serial correlation using xtserial for the 
> regression without instruments. Is there a way to test for 
> autocorrelation when instrumental variables are present? Is 
> there a way to combine the xtregar command with instrumental 
> variables?
> 3. One variable enters as INCOME/PRICE. How can I tell Stata 
> to use Instrumental variables for PRICE and then to divide 
> Income by Price?
>  
> Thank you for any  comments!
> Philio
> -- 
> 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