TY  - JOUR
AU  - Nevo,Aviv
AU  - Rosen,Adam M.
TI  - Identification with Imperfect Instruments
JF  - National Bureau of Economic Research Working Paper Series
VL  - No. 14434
PY  - 2008
Y2  - October 2008
UR  - http://www.nber.org/papers/w14434
L1  - http://www.nber.org/papers/w14434.pdf
N1  - Author contact info:
Aviv Nevo
Department of Economics
Northwestern University
2001 Sheridan Road
Evanston, IL 60208-2600
Tel: 847/491-8212
Fax: 847/491-7001
E-Mail: nevo@northwestern.edu

Adam M. Rosen
Department of Economics
Gower Street
London WC1E 6BT
E-Mail: adam.rosen@ucl.ac.uk
AB  - Dealing with endogenous regressors is a central challenge of applied research. The standard solution is to use instrumental variables that are assumed to be uncorrelated with unobservables. We instead assume (i) the correlation between the instrument and the error term has the same sign as the correlation between the endogenous regressor and the error term, and (ii) that the instrument is less correlated with the error term than is the endogenous regressor. Using these assumptions, we derive analytic bounds for the parameters. We demonstrate the method in two applications.
ER  -