Sandra,
Interesting problem, but I would like to know some details...
(1) are you using 1 instruments?
(2) what are these variables y, x and z (the instrument)?
(3) is your IV estimate significant?
(4) what did you get with LIML? significant?
As Kit said if the fitting x versus z is poor then your results
will poor. Then LIML must have a huge CI.
Rodrigo.
----- Original Message -----
From: "Mortal, Sandra C." <mortals@missouri.edu>
To: <statalist@hsphsun2.harvard.edu>
Sent: Saturday, February 03, 2007 10:44 PM
Subject: st: RE: ivreg2
Hi Kit,
Thanks for your prompt response. If you don't mind I would like to ask
you a few more questions.
(1) If the bias of the IV estimates cause them to approach the
(inconsistent) OLS estimates (which are significantly positive), then if
I get larger IV estimates (compared to the OLS estimates) does that mean
my estimates would be even larger if I had strong instruments? In other
words, would that imply my IV estimates are biased downward?
(2) I read a review by Stock and co-authors, and they mention that if I
estimate my equation using liml, then my results will be more robust to
weak instruments, further, I noticed that the Stock-Yogo critical values
are much lower, when I use LIML. Am I making a correct intepretation of
their text?
(3) In the review by Stock and co-authors, they mention that the rule
of thumb is that an F-test should be greater than 10. They also mention
in the context of multiple instrumental variables the Cragg-Donald F
statistic and the Stock-Yogo critical values. Does this Cragg-Donald
statistic also work in a one instrument context? This is because, when
I look at this statistic my instruments seem to be higher than the 10%
Stock-Yogo critical value. If each of these statistics work as a
sufficient condition (rather than a necessary condition) for having
strong instruments, then I would rather report the Cragg-Donald
statistic, considering this is statistically sound.
My problem is that it is very tough to get exogenous instruments for my
variable, and this is the only instrument I have managed to come up
with, so I would like to stick to it, if at all possible.
Thanks a lot for your help,
Sandra
***********************************************
Sandra Mortal
Assistant Professor of Finance
516 Cornell Hall
University of Missouri
Columbia, MO 65211
Office: (573) 884-1684
Fax: (573) 884-6296
***********************************************
-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Kit Baum
Sent: Saturday, February 03, 2007 7:25 PM
To: statalist@hsphsun2.harvard.edu
Subject: st: ivreg2
Sandra asks
I am using instrumental variables and have a weak instrument,
according to the F-test. I only have one endogenous variable and my
sample is large. I wonder if there are better statistics to investigate
if an instrument is weak (perhaps the Hahn and Hausman test testing the
null hypothesis that the instrument is strong), and if stata supports
these statistics. I also would like to ask if stata contains any
routine that would provide estimates robust to weak instruments.
Diagnosis of instruments' weakness is complicated when there are
multiple endogenous regressors. When there is only one, it is simple:
if the single first-stage regression fits poorly, you have weak
instruments, and the IV estimates will suffer. We have recently added
diagnostics by Stock and Yogo for the weak instruments case. In the
presence of weak instruments, the bias of the IV estimates cause them to
approach the (inconsistent) OLS estimates.
There is no such thing as 'estimates robust to weak instruments'. You
are using instruments to generate consistent estimate of the equation,
and if the instruments are only weakly correlated to the endogenous
variable, your results will be poor. The way to render them robust is to
get better instruments.
Kit
Kit Baum, Boston College Economics
http://ideas.repec.org/e/pba1.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/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* 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/
*
* 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/