Simultaneous confidence bands in a zero-inflated regression model for binary data

Abstract The logistic regression model has become a standard tool to investigate the relationship between binary outcome and set of potential predictors. When analyzing data, it often arises, however, that observed proportion zeros is greater than expected under postulated model. Zero-inflated binomial (ZIB) models have been developed fit data contain too many zeros. Maximum likelihood estimators in these proposed, their asymptotic properties were recently established. In this paper, we use construct simultaneous confidence bands for probability positive ZIB Simultaneous are especially attractive since they allow inference be made over whole regressor space. We two types bands, based on: (i) Scheffé method linear model; (ii) Monte Carlo simulations approximate distribution supremum Gaussian field indexed by regressor. finite-samples investigated compared simulation study.