Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: endogenous variable with missing

From   sara borelli <>
Subject   st: endogenous variable with missing
Date   Fri, 16 Mar 2007 04:08:46 +0100 (CET)

Dear Statalist members

I have a couple of questions.
I have the following system of simultaneous equations:

Q= b1*Zq + b2*W +  e     i=1....N  
[Q observed over whole sample]

W= a1*Zw + a2*Q + u      i=1...n < N  
[W observed only for  sub-sample i=1...n<N and missing
for the rest of observations ]

I want to estimate eqn Q for the whole sample. If I
use standard IV the command gives me estimate only for
the subsample for which W is observed. I have been
told to estimate a reduced form of equation W, then
predict W for the whole sample and insert it in the
second stage in the eqn for Q.
Could anyone confirm this?

Second, how should I proceed if D is actually censored
and I want estimated it by tobit?

thank you in advance for any suggestion



L'email della prossima generazione? Puoi averla con la nuova Yahoo! Mail:
*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index