This is a line for the server to eat
http://www.stata-journal.com/article.html?article=st0136
HTH
Martin
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of francesca.modena
Sent: Tuesday, October 28, 2008 12:40 PM
To: [email protected]
Subject: st: propensity score and mills ratio
Dear all,
This is a classical problem of treatment effect.
I have two outcomes:
Y1i: the outcome of unit i if i were exposed to the treatment (T=1)
Y0i: the outcome of unit i if i were not exposed to the treatment (T=0)
I want to regress Y1i on a set of characteristics Z. OLS regression of Y1i
on Z can be biased because of sample selection problem.
Let us assume that the probability of being exposed to the treatment can be
described by a probit equation
Ti = alpha*X + error
>From the probit equation I can derive the selection terms for the two
groups
T=0 and T=1 (i.e. inverse mills ratio)
Now I can consistently regress Y1i on Z for the sample with T=1, augmenting
the regression with the corresponding selection term (i.e. I include the
mills ratio for those with T=1 in the regression).
Another procedure to deal with selection bias is the propensity score
matching. If I am right the Stata commands are:
pscore treat X, pscore(scorename)
attr Y1i treat, pscore(scorename) (Is this equation estimated on all the
sample or only for those with T=1 or T=0?)
What is the difference between the two procedures? Can I use both mills
ratio and propensity score to deal with selection problems?
Thanks
Francesca
*
* 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/
*
* 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/
