Seminar

Inference for functions of partially identified parameters in moment inequality models

Speaker

Federico A. Bugni

Date & Time

18 February 2014

Type

Seminar

Venue

The Institute for Fiscal Studies
7 Ridgmount Street,
Fitzrovia,
London,
WC1E 7AE

This paper introduces a new hypothesis test for the null hypothesis H0 : f(0) = 0, where f(.) is a known function, 0 is a known constant, and 0 is a parameter that is partially identified by a moment (in)equality model.

The main application of our test is sub-vector inference in moment inequality models, that is, for a multidimensional , the function f(0) = k selects the kth coordinate of 0.

Our test controls asymptotic size uniformly over a large class of distributions of the data and has better asymptotic power properties than currently available methods. In particular, we show that the new test has asymptotic power that dominates the one corresponding to two existing competitors in the literature: subsampling and projection-based tests.

The paper for this seminar can be downloaded here.