题 目：Inferences in Two-Step Semiparametric Partially Identi.ed Models

报 告 人：Lin Zhu, Tsinghua University

时 间：2013年4月11日（周四）14:00---15:30

地 点：拉斯维加斯9888新楼217室

Abstract:

This paper provides inference tools for partially identi.ed semiparametric models. The main

working assumption is that the .nite-dimensional parameter of interest and the in.nite-dimensional

nuisance parameters are identi.ed conditionally on other nuisance parameters being known. This

structure arises in numerous applications and permits the use of standard tools from empirical

processes theory. We develop uniform convergence for the set of estimates and use the uniformity

to establish set inference. We allow for the identi.ed set of nuisance parameters to be unknown and

estimated, which in general requires to establish inference under misspeci.cation. The latter is also

useful in a formal development of sensitivity analysis. Inference is implemented with a multiplier-

type bootstrap. Several examples illustrate the wide applicability of our results.