Econometrica: Mar, 1994, Volume 62, Issue 2
Testing Instrument Admissibility: Some Refined Asymptotic Results
https://doi.org/0012-9682(199403)62:2<373:TIASRA>2.0.CO;2-T
p. 373-403
Michael A. Magdalinos
This paper is concerned with the refined asymptotic properties of several tests for the admissibility of a subset of (overidentifying) instrumental variables. It derives maximum likelihood (ML) and linearized ML tests and calculates size corrections to the order 1/T. The local power function of the size-corrected tests is the same to the order 1/T, irrespective of the form of the test statistic or the limited information estimator used in its computation. Finally, it compares these tests with two previously proposed tests.