Speaker: Xiaoxia Shi (University of Wisconsin-Madison)

Time: 15:10 - 17:00 p.m., Apr 17, 2025, GMT+8

Venue: Rm 217, Guanghua Building 2, PKU

Abstract: 

This paper proposes a new test for inequalities that are linear in possibly partially identified nuisance parameters, called the generalized conditional chi-squared (GCC) test. The GCC test is applicable to a broad set of inequality testing problems, including subvector inference and specification testing for linear unconditional moment (in)equality models and inference for parameters bounded by linear programs. The new test uses a two-step GMM type test statistic and a chi-squared critical value with a data-dependent freedom that can be calculated by an elementary formula. Its simple structure and tuning-parameter-free implementation makes it attractive for practical use. We establish uniform asymptotic validity of the test and demonstrate its good power in Monte Carlo simulations.

Source: Guanghua School of Management, PKU