I am trying to calculate some statistics for weak instruments in Stata,
and some of the previous statalist questions seem to indicate that
ivreg2 combined with the "ffirst" option will report the Cragg-Donald
statistic.
When I type the following (variable names are unimportant):
ivreg2 sperce rbd11 - rbd15 (age xrep xstartlate = c2-c5), ffirst
it gives the following output...
First-stage regressions
-----------------------
Summary results for first-stage regressions:
Shea
Variable Partial R2 Partial R2 F( 4,196341) P-value
age 0.0024 0.6450 89191.70 0.0000
xrep 0.0001 0.0090 444.08 0.0000
xstartlate 0.0000 0.0302 1528.72 0.0000
Instrumental variables (2SLS) regression
----------------------------------------
Number of obs =
196351
F( 8,196342) =
213.66
Prob > F =
0.0000
Total (centered) SS = 192791.2461 Centered R2 =
-0.0363
Total (uncentered) SS = 192793.6585 Uncentered R2 =
-0.0363
Residual SS = 199790.6129 Root MSE =
1
------------------------------------------------------------------------------
sperce | Coef. Std. Err. z P>|z| [95% Conf.
Interval]
-------------+----------------------------------------------------------------
age | .1938617 .1800731 1.08 0.282 -.159075
.5467984
xrep | -1.434245 2.340419 -0.61 0.540 -6.021383
3.152893
xstartlate | -1.292564 2.913459 -0.44 0.657 -7.002838
4.41771
rbd11 | -.0002252 .0007117 -0.32 0.752 -.0016201
.0011697
rbd12 | 1.03e-06 2.68e-06 0.38 0.701 -4.23e-06
6.29e-06
rbd13 | -1.70e-09 4.00e-09 -0.43 0.671 -9.53e-09
6.13e-09
rbd14 | 1.15e-12 2.57e-12 0.45 0.655 -3.88e-12
6.18e-12
rbd15 | -2.75e-16 5.94e-16 -0.46 0.644 -1.44e-15
8.90e-16
_cons | -1.854898 1.857435 -1.00 0.318 -5.495405
1.785608
------------------------------------------------------------------------------
Sargan statistic (overidentification test of all instruments):
1.102
Chi-sq(1) P-val =
0.29386
------------------------------------------------------------------------------
Instrumented: age xrep xstartlate
Instruments: c2 c3 c4 c5 rbd11 rbd12 rbd13 rbd14 rbd15
------------------------------------------------------------------------------
I expected to see the underidentification diagnostics, but they do not
appear. Is there and update I need for ivreg2 that will give this
information?
Thank you,
Justin Smith
*
* 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/
