Statalist


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

Re: st: Interesting Results - But Am I Right?


From   Austin Nichols <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Interesting Results - But Am I Right?
Date   Sun, 26 Apr 2009 08:07:36 -0400

Sachin Chintawar <schint1@tigers.lsu.edu>:
Probably you are greatly increasing the strength of the instruments as
you increase the number of instruments--you can check the first-stage
stats with e.g. -ranktest- on SSC (see also -ivreg2- on SSC for
context), or derive analytically the concentration parameter or
equivalent (see e.g.
http://ksghome.harvard.edu/~jstock/ams/websupp/rfa_7.pdf and related
material).  A more natural model is one where the additional
instruments do not have substantial additional explanatory power for
the endog var, i.e. you have 4 essentially identical instruments
differing from each other only via some noise, any one of which would
be a mediocre instrument, and putting all 4 in actually is worse than
just using one.

On Fri, Apr 24, 2009 at 5:00 PM, Sachin Chintawar
<schint1@tigers.lsu.edu> wrote:
> Dear Statalist Users
> I have been playing around with endogenous variable models and the
> hypothsis that 'An increase in instruments tend to increase the bias
> of our estimates'. While this was shown to be true by A. Buse 'The
> Bias of Instrumental Variable Estimators' in Econometrica (1992). My
> simulation results showed the contrary (A simple variation was that
> this was a probit model - Thanks to Mr. Martin for the million
> questions while I was coding it). The program until now is given
> below. Under the conditions specified I see that as I increase the
> instuments (from z1 to z4) the bias in the 'beta' value actually
> decreases. My question is
> 1. Am I specifying everything in the model right?
> 2. Why this difference in results from another paper?
*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index