A1156
Title: Missing endogenous variables in conditional moment restriction models
Authors: Antonio Cosma - University of Bergamo (Italy) [presenting]
Andrei Kostyrka - University of Luxembourg (Luxembourg)
Gautam Tripathi - university of Luxembourg (Luxembourg)
Abstract: The focus is on estimating finite dimensional parameters identified via a system of conditional moment equalities when at least one of the endogenous variables (which can either be endogenous outcomes, endogenous explanatory variables, or both) is missing for some individuals in the sample. The semiparametric efficiency bound is derived for estimating the parameters, and it is used to demonstrate that if all of the endogenous variables in the model are missing, then estimation using only the validation subsample (the subsample of observations for which the endogenous variables are nonmissing) is asymptotically efficient. An estimator based on the full sample is also proposed that achieves the semiparametric efficiency bound. A simulation study reveals that the estimator can work well in medium-sized samples and that the resulting efficiency gains (measured as the ratio of the variance of an efficient estimator based on the validation sample and the variance of the estimator) are comparable with the maximum gain the simulation design can deliver.
