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

st: 2SLS estimation with possible scaling

From   Renuka Metcalfe <>
To   statalist <>
Subject   st: 2SLS estimation with possible scaling
Date   Wed, 20 Feb 2008 12:41:31 +0000 (GMT)

Dear Statalisters

I have estimated 2SLS regressions. The data is
cross-section and the endogenous explanatory variable
is binary, I have used

. probit x x1 x2 x3 z

where x = endogen. binary rhs variable

I then took the predicted values and ran an -ivreg-
with the predicted values. I find that the coefficient
of the endogenous variable is 1.05 and is significant.
I guess I could scale the endogenous variable without
scaling anything as yet. I did this and I find the
coefficient of the endogenous variable is now 0.105
and has the same significance, that is, it is
significant. But I am not certain, if would be
I would be grateful, if anyone would let me know if
just scaling the endogenous variable is sufficient. I
am not certain if I should scale the dependent
variable of the ivreg and also the instrument I used
in the first stage regression and the predicted values
if this is possible.

Thank you

Sent from Yahoo! Mail - a smarter inbox

*   For searches and help try:

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