A0233
Title: Efficient estimation of a semiparametric zero-inflated Bernoulli regression model
Authors: Chin-Shang Li - University at Buffalo (United States) [presenting]
Abstract: When the observed proportion of zeros in a data set consisting of binary outcome data is larger than expected under a regular logistic regression model, it is frequently suggested using a zero-inflated Bernoulli (ZIB) regression model. A spline-based ZIB regression model is proposed to describe the potentially non-linear effect of a continuous covariate. A spline, which can be expressed as a linear combination of B-spline basis functions, is used to estimate the unknown smooth function. The spline estimator of the nonparametric component is shown to be uniformly consistent and achieve the optimal convergence rate under the smoothness condition. The regression parameter estimators are shown to be asymptotically normal and efficient. A spline-based semiparametric likelihood ratio test is established, and a direct and consistent variance estimation method based on least-squares method is proposed. Extensive simulations are conducted to evaluate the finite-sample performance of the proposed method. A real-life data set is used to illustrate the practical use of the proposed methodology.
