In modeling count data with over- or under-dispersion and extra or few zeros, si- multaneously, generalized Poisson hurdle regression is an appropriate model to describe the relationship between the count response variable and some predictor variables. To improve the estimation of count parameters in the generalized Poisson hurdle, Liu-type shrinkage estimators were suggested under a linear restriction on these parameters when there exists multicollinearity problem. The performance of the proposed estimators numerically was compared to Liu-type unrestricted estimator in terms of their relative efficiency by conducting a Monte Carlo simulation study. Finding results confirmed that the proposed estimators perform superiorly better than the Liu-type unrestricted estimator.
