st: RE: re: overid

 From "Schaffer, Mark E" To Subject st: RE: re: overid Date Tue, 1 Dec 2009 16:16:43 -0000

```Hi all.  For anyone who is interested in the detail of the different
overid stats generated by -overid- after 2SLS and -reg3-, here is an
illustration.  (First read Kit's posting below.)

The usual single-equation Sargan statistic is often calculated as an
N*R-sq following an artificial regression.  Sometimes in the literature
you will see a reference to a Sargan stat with a degrees of freedom
correction, i.e., (N-L)*R-sq, where L is the number of regressors.

If you use -overid- after -reg3- where the latter is used to do 2SLS,
you will get the latter form of the Sargan stat.  If you include the
-nodfk- option with -reg3- and then run -overid-, you get the first and
more common version of the Sargan stat.  The Stata output below
illustrates.

--Mark

. use http://fmwww.bc.edu/ec-p/data/hayashi/griliches76.dta, clear
(Wages of Very Young Men, Zvi Griliches, J.Pol.Ec. 1976)

. * Standard Sargan statistic with no dof correction
. qui ivreg2 lw s expr tenure rns smsa  (iq=med kww age mrt)

. di %10.7f e(j)
61.1365980

. qui reg3 (lw =iq s expr tenure rns smsa), endog(iq) exog(med kww age
mrt s expr
> tenure rns smsa) 2sls nodfk

. qui overid

. di %10.7f r(crit)
61.1365980

.
. * Sargan stat with dof correction
. qui ivreg2 lw s expr tenure rns smsa  (iq=med kww age mrt)

. overid, all

Tests of overidentifying restrictions:
Sargan N*R-sq test       61.137  Chi-sq(3)    P-value = 0.0000
Sargan (N-L)*R-sq test   60.572  Chi-sq(3)    P-value = 0.0000
Basmann test             65.623  Chi-sq(3)    P-value = 0.0000
Sargan pseudo-F test     20.191  F(3,751)     P-value = 0.0000
Basmann pseudo-F test    21.874  F(3,748)     P-value = 0.0000

. di %10.7f r(sargan2)
60.5720120

. qui reg3 (lw =iq s expr tenure rns smsa), endog(iq) exog(med kww age
mrt s expr
> tenure rns smsa) 2sls

. qui overid

. di %10.7f r(crit)
60.5720120

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Kit Baum
> Sent: 01 December 2009 00:34
> To: statalist@hsphsun2.harvard.edu
> Subject: st: re: overid
>
> <>
> An earlier exchange discussed the behavior of
> overidentification test statistics via -overid- (SSC: Baum,
> Schaffer, Stillman & Wiggins) after -reg3- and -reg3, 2sls-.
> We have corresponded StataCorp developers, and they have
> pointed out that some of the differences we identified were
> arising because of degrees-of-freedom adjustments. If the
> -2sls- option on -reg3- is used, the -nodfk- option should
> also be invoked. Then reg3, applied to a single equation,
> will yield the same Sargan statistic as single-equation
> estimation via -ivreg2- or -ivregress-.
>
> If -reg3- is used to estimate multiple equations, its
> estimated coefficients and covariance matrix will differ if
> the -2sls- option is specified (w/w/o -nodfk-). In that
> instance, the Sargan statistic after -reg3, 2sls- will not
> match that of -overid- after -reg3, 3sls-. If the full 3SLS
> estimator is used, the Sargan statistics of -ivreg2-,
> -ivregress- and -reg3- will match.
>
> As far as we can see, both official -reg3- and user-written
> -overid- after -reg3- are behaving perfectly.
>
> Kit and Mark
>
> Kit Baum   |   Boston College Economics & DIW Berlin   |
> http://ideas.repec.org/e/pba1.html
>                               An Introduction to Stata
> Programming  |   http://www.stata-press.com/books/isp.html
>    An Introduction to Modern Econometrics Using Stata  |
> http://www.stata-press.com/books/imeus.html
>
>
> *
> *   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/
```