Semiparametric Estimationwith GeneratedCovariates

Abstract

We study a general class of semiparametric estimators when the infinite-dimensional nuisance parameters include a conditional expectation function that has been estimated nonparametri- cally using generated covariates. Such estimators are used frequently to e.g. estimate nonlinear models with endogenous covariates when identification is achieved using control variable tech- niques. We study the asymptotic properties of estimators in this class, which is a non-standard problem due to the presence of generated covariates. We give conditions under which estimators are root-n consistent and asymptotically normal, derive a general formula for the asymptotic variance, and show how to establish validity of the bootstrap.