Mathematics and Statistics Faculty Publications


Regression Analysis Under Complex Probability Sampling Designs in Presence of Many Zero-value Responses

Document Type



In this article, we extend Chen et al.’s [4] results to the zero-inflated regression model under complex probability sampling designs. Regression models for zero-inflated population have been considered in the literature for a long time. However, many of the zero-inflated regression models in the literature aim at count data, though the regression models with continuous-type responses are even more often to be seen in applications. Furthermore, these regression models do not address the situations when the data available for analysis are obtained through complex probability sampling designs. In this paper, we investigate the estimation problem in generalized linear regression models (continuous-type or discrete-type) and develop the zero-inflated mixture (ZIM) regression model under complex probability sampling designs via two-component mixture models where the probability distribution of non-zero component is supposed to be parametric. The maximum pseudo-likelihood procedure is proposed to be used in estimating the expected responses at “future” covariate values/vectors. Simulation studies are conducted to assess the performance of the proposed procedure. The simulation results show that under some complex probability sampling designs, the new confidence intervals based on the pseudo-likelihood function perform significantly better than the standard/classic procedures. The proposed pseudo-likelihood new procedure is applied to a real-life data set that was analyzed by many other authors.

Publication Date


Publication Title

Advances and Applications in Statistics





Start Page No.


End Page No.


This document is currently not available here.