Subgroup analysis for zero-inflated count panel data

Zero-inflated Poisson (ZIP) regression model is widely used for count data with excess zeros. In this paper, we propose a zero-inflated Poisson mixed effects model to account for the correlation among repeated measurements and identify subgroups in heterogeneous populations. We develop an iterative algorithm to estimate the subgroup assignments and corresponding regression coefficients for all individuals, with the number of subgroups determined by the averaging cross-validation (CVA) method. Under mild assumptions, the proposed estimator exhibits consistency and asymptotically follows a normal distribution. The effectiveness of our method is demonstrated through extensive simulation studies and an application to a real dataset.