Restricted almost unbiased Liu-estimator in zero-inflated Poisson regression model

Abstract

The Liu shrinkage estimators for the zero-inflated Poisson regression model (ZIPRM) has been a suitable shrinkage method to reduce the impacts of multicollinearity. The zero-inflated Poisson regression model (ZIPRM) is a very popular model for count data that have extra zeros. However, it is known that the presence of multicollinearity can have a negative effect on the variance of the maximum likelihood estimator (MLE) of the ZIPRM coefficients. In this work, an Restricted almost unbiased Liu-estimator in zero-inflated Poisson regression (RAULZIPR) model is proposed the presence of multicollinearity. We investigate the behavior of the proposed estimator Based on a Monte Carlo study. we illustrate that our proposed estimators exhibit better MSE than the usual MLE estimator, Liu estimator and ZIPRidge estimator in the presence of multicollinearity. Furthermore, we apply the proposed estimator on a real dataset. The results show that the performance of (RAULZIPR) outperforms for that of the MLE estimator, Liu estimator and ZIPRidge estimator in the existing of the multicollinearity among the count data in the (ZIPRM)model.