Department of Public Health Sciences

A lack-of-fit test for parametric zero-inflated Poisson models

Li, C.S

Journal of Statistical Computation and Simulation. 2011. 81(9):1081-1098.

Count data often contain many zeros. In parametric regression analysis of zero-inflated count data, the effect of a covariate of interest is typically modelled via a linear predictor. This approach imposes a restrictive, and potentially questionable, functional form on the relation between the independent and dependent variables. To address the noted restrictions, a flexible parametric procedure is employed to model the covariate effect as a linear combination of fixed-knot cubic basis splines or B-splines. The semiparametric zero-inflated Poisson regression model is fitted by maximizing the likelihood function through an expectation–maximization algorithm. The smooth estimate of the functional form of the covariate effect can enhance modelling flexibility. Within this modelling framework, a log-likelihood ratio test is used to assess the adequacy of the covariate function. Simulation results show that the proposed test has excellent power in detecting the lack of fit of a linear predictor. A real-life data set is used to illustrate the practicality of the methodology.

Close Window

UC Davis Health System is pleased to provide this information for general reference purposes only. It should not be considered as a substitute for professional medical advice. You are urged to consult with your health care provider for diagnosis of and treatment for any health-related condition. The information provided herein may not and should not be used for diagnosis and treatment.

Reproduction of material on this web site is hereby granted solely for personal use. No other use of this material is authorized without prior written approval of UC Regents.