Instrumental Variable
Regression II
(Fall 2010)
Lecture 20
Seyhan Erden Arkonac, PhD
Problem Set 8 is posted, it is due on
Tuesday, November 23rd
1

This
** preview**
has intentionally

**sections.**

*blurred***to view the full version.**

*Sign up*
2
The General IV Regression Model
(SW Section 12.2)
So far we have considered IV regression with a single
endogenous regressor (
X
) and a single instrument (
Z
).
We need to extend this to:
multiple endogenous regressors (
X
1
,…,
X
k
)
multiple included exogenous variables (
W
1
,…,
W
r
)
These need to be included for the usual OV reason
multiple instrumental variables (
Z
1
,…,
Z
m
)
More (relevant) instruments can produce a smaller
variance of TSLS:
the
R
2
of the first stage increases, so
you have more variation in
ˆ
X
.
Terminology: identification & overidentification