Rateb,
Your interpretation of the Sargan test statistic is correct.
However, 90 degrees of freedom is a lot, and it's possible that test
has very little power if you use a lot of instruments, esp. if the
number of observations isn't very large. You might try reestimating
using a smaller number of lags as a test of the robustness of your
results.
Hope this helps.
--Mark
Date sent: Thu, 14 Apr 2005 15:20:42 +1000 (EST)
From: "Rateb Abu-Sharia" <[email protected]>
To: [email protected]
Subject: st: the Sargan test
Send reply to: [email protected]
> Dear Sir/Madam:
>
> In reference to GMM methods in STATA8 (Arellano and Bond model,
> xtabond), I am trying to introduce instrumental variables to fix the
> endogeneity problem caused by fixed and random effects regressions.
>
> I have a question concerning the Sargan test of over-identifying
> restrictions after using the recommended two-step specification, I find
> the Sargan test for all cases in my study with p-value equal 1
> suggesting not to reject the over-identifying restrictions, as follows:
>
> Sargan test of over-identifying restrictions:
> chi2 (90) = 0.00 Prob > chi2 = 1.0000
>
> However, Does it �P-value equal one� means that I am working on the
> right practice of the �Sargan test� or is there any problem with this P-
> value? If any, could you give me please your advice to which value
> should I rely on? I look forward to your response.
>
> Your cooperation would be much appreciated.
>
>
>
> Many thanks
>
> Rateb Abu-Sharia
> School of Economics & Finance
> University of Western Sydney
> Phone: +61 2 9890 3245
> Mob. +61 405 114 031
>
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
Prof. Mark E. Schaffer
Director
Centre for Economic Reform and Transformation
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS UK
44-131-451-3494 direct
44-131-451-3296 fax
44-131-451-3485 CERT administrator
http://www.sml.hw.ac.uk/cert
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
