Sung Jae Jun, Brown University, will be at the department on Friday 20 January. He is a job candidate for the position as micro-econometrician. His job talk takes place at 2:00pm in Savery 302. Title and abstract below. Weak Identification Robust Tests in an Instrumental Quantile Model
ABSTRACT: We consider the linear instrumental quantile model proposed by Chernozhukov and Hansen (2001, 2005a, 2005b). Since it is never clear for what quantile effects the given instruments are most informative, we develop a testing procedure that is robust to identification quality in the GMM framework. In order to reduce the computational burden, a multi-step approach is taken, and a two-step Anderson-Rubin (AR) statistic is considered. We then propose a three-step orthogonal decomposition of the AR statistic, where the null distribution of each component does not depend on the assumption of a full rank of the Jacobian. Power experiments are conducted, and inferences on returns to schooling using the Angrist and Krueger data are considered as an empirical example. Although returns to schooling for the upper quantiles seem to be quite consistent, the robust confidence sets for the lower quantiles are so wide that they still remain imprecise, which differs from the results in Lee (2004) and Chernozhukov and Hansen (2005b).