Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: Test for Strict Exogeneity after FD


From   Lukas Borkowski <[email protected]>
To   [email protected]
Subject   Re: st: Test for Strict Exogeneity after FD
Date   Sat, 19 May 2012 14:57:51 +0200

Dear Foly,

thanks for your reply - but I figured it out - and the solution might be interesting for some others as well, so I give a quick explanation. After regressing the first-differenced equation, I wanted to check if differencing had solved the endogeneity concern, thus if the strict exogeneity assumption would hold. As Wooldridge (2002, p.285f) suggests, it is quite easy to run this test if your panel has just two time periods - you do not even have to run the hausman test. All what you need is to include one or several of your explanatory variables in your first-differenced equation and to carry out a F-test for significance of these included variables. Failing to reject the null means that differencing has solved the endogeneity concern. Check "Felbermayr, Jung 2002: The pro-trade effect of the brain drain: Sorting out confounding factors" for an example.


#
Lukas Borkowski



Am 19.05.2012 um 14:33 schrieb Foly Ananou:

>  Dear Lukas, 
>  Can U explain how u are trying to run the test on stata ? ? May Be  
>  knowing what u have tried, we could be able to give some suitable  
>  answer. 
>  Thx. 
>  Foly Ananou 
> 
> 
> 
>> ________________________________ 
>> 
>>  -passez vos annonces gratuitement cliquez ici 
>> <http://www.bicoeur.com/> 
>> 
>> <http://www.bicoeur.com/> 
>> 
>> 
>> 
>> 
>>> From: [email protected] 
>>> Subject: st: Test for Strict Exogeneity after FD 
>>> Date: Sat, 19 May 2012 11:37:19 +0200 
>>> To: [email protected] 
>>> 
>>> Dear all, 
>>> 
>>> I am using Stata 11.2. 
>>> 
>>> I am working on panel data with just two time periods and applied  
>> first-differencing to compute a FD-estimator. In Wooldridge (2002):  
>> Econometric Analysis of cross-section and panel data, page 285 I came  
>> across a very appealing way to somehow run the hausman test after FD to  
>> test for strict exogeneity. However, after trying for ages, I do still  
>> not know how to do that in Stata. 
>>> 
>>> My question is: How do I test for strict exogeneity (via Hausman or  
>> elsewise) after running FD? What is the command? 
>>> 
>>> Thank you so much for your help! 
>>> 
>>> 
>>> # 
>>> Lukas Borkowski 
>>> 
>>> 
>>> 
>>> 
>>> * 
>>> * 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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index