Model selection tests for moment inequality models

A-Tier
Journal: Journal of Econometrics
Year: 2015
Volume: 187
Issue: 1
Pages: 1-17

Score contribution per author:

4.022 = (α=2.01 / 1 authors) × 2.0x A-tier

α: calibrated so average coauthorship-adjusted count equals average raw count

Abstract

We propose Vuong-type tests to select between two moment inequality models based on their Kullback–Leibler distances to the true data distribution. The candidate models can be either non-overlapping or overlapping. For each case, we develop a testing procedure that has correct asymptotic size in a uniform sense despite the potential lack of point identification. We show both procedures are consistent against fixed alternatives and local alternatives converging to the null at rates arbitrarily close to n−1/2. We demonstrate the finite-sample performance of the tests with Monte Carlo simulation of a missing data example. The tests are relatively easy to implement.

Technical Details

RePEc Handle
repec:eee:econom:v:187:y:2015:i:1:p:1-17
Journal Field
Econometrics
Author Count
1
Added to Database
2026-01-29