DIRECT SEMIPARAMETRIC ESTIMATION OF SINGLE-INDEX MODELS WITH DISCRETECOVARIATES

Others have developed average derivative estimators of the parameter b eta in the model E(Y\X = x) = G(x beta), where G is an unknown functio n and X is a random vector. These estimators are noniterative and easy to compute but require that X be continuously distributed. This artic le develops a noniterative, easily computed estimator of beta for mode ls in which some components of X are discrete. The estimator is n(1/2) consistent and asymptotically normal. An application to data on produ ct innovation by German manufacturers illustrates the estimator's usef ulness.