This study develops a framework for testing hypotheses on structural parameters in in-complete models. Such models make set-valued predictions and hence do not generally yield a unique likelihood function. The model structure, however, allows us to construct tests based on the least favorable pairs of likelihoods using the theory of Huber and Strassen (1973). We develop tests robust to model incompleteness that possess certain optimality properties. We also show that sharp identifying restrictions play a role in constructing such tests in a computationally tractable manner. A framework for analyzing the local asymptotic power of the tests is developed by embedding the least favorable pairs into a model that allows local approximations under the limits of experiments argument. Examples of the hypotheses we consider include those on the presence of strategic interaction eﬀects in discrete games of complete information. Monte Carlo experiments demonstrate the robust performance of the proposed tests.
9 December 2019
Working Paper (CWP68/19)