TY  - CHAP
AB  - In the context of competing IV econometric models and estimators, we demonstrate a semiparametric Stein-like estimator (SSLE) that, under quadratic loss, has superior risk performance. The method eliminates the need for pretesting to decide whether covariate endogeneity is present and makes use of a pretest estimator choice between IV and non-IV methods unnecessary. A sampling study is used to illustrate finite sample performance over a range of sampling designs, including its performance relative to pretest estimators. An important applied problem from the literature is analyzed to indicate possible applied implications and the relation of SSLE to other modern IV estimators.
VL  - 30
SN  - 978-1-78190-309-4, 978-1-78190-310-0/0731-9053
DO  - 10.1108/S0731-9053(2012)0000030013
UR  - https://doi.org/10.1108/S0731-9053(2012)0000030013
AU  - Judge George G.
AU  - Mittelhammer Ron C.
ED  - Dek Terrell
ED  - Daniel Millimet
PY  - 2012
Y1  - 2012/01/01
TI  - A Risk Superior Semiparametric Estimator for Overidentified Linear Models
T2  - 30th Anniversary Edition
T3  - Advances in Econometrics
PB  - Emerald Group Publishing Limited
SP  - 237
EP  - 255
Y2  - 2024/04/19
ER  -