TY  - JOUR
AU  - Inoue,Atsushi
AU  - Solon,Gary
TI  - Two-Sample Instrumental Variables Estimators
JF  - National Bureau of Economic Research Technical Working Paper Series
VL  - No. 311
PY  - 2005
Y2  - June 2005
UR  - http://www.nber.org/papers/t0311
L1  - http://www.nber.org/papers/t0311.pdf
N1  - Author contact info:
Atsushi Inoue
North Carolina State University
Department of Agricultural and Resource Economics,
Raleigh, NC 27695-8109
E-Mail: atsushi@ncsu.edu

Gary Solon
Department of Economics
Michigan State University
East Lansing, MI 48824-1038
Tel: 517/353-9933
Fax: 517/432-1068
E-Mail: solon@msu.edu
AB  - Following an influential article by Angrist and Krueger (1992) on two-sample instrumental variables (TSIV) estimation, numerous empirical researchers have applied a computationally convenient two-sample two-stage least squares (TS2SLS) variant of Angrist and Krueger's estimator. In the two-sample context, unlike the single-sample situation, the IV and 2SLS estimators are numerically distinct. Our comparison of the properties of the two estimators demonstrates that the commonly used TS2SLS estimator is more asymptotically efficient than the TSIV estimator and also is more robust to a practically relevant type of sample stratification.
ER  -