Models for Zero Truncated Count Data in Medicine and Insurance
It is important to match count data with appropriate model(s), models such as Poisson Regression, Quassi Poisson, Negative Binomial, to name, but researchers have adopted a few to suit zero truncated count data in the past. Dedicated models for fitting zero truncated count data have been developed in recent times, and are considered adequate. This study proposed the zero truncated Poisson and MCMCglmms Poisson regression model of the Bayesian multi-level Poisson and Bayesian multi-level Geometric model, Bayesian Monte Carlo Markov Chain Generalized Linear Mixed Models (MCMCglmms) to match health count data truncated at zero. Data on doctor visits to patients under the National Health Insurance System in Nigeria was collected and used to match the models. To decide preferred models for the fitting of zero truncated data, acceptable model selection criteria were used. Results obtained showed that Bayesian multi-level Poisson outperformed Poisson Geometric multi-level Bayesian model; MCMCglmms of zero truncated Poisson also outperformed MCMCglmms Poisson.
Dr. Olumide S. Adesina
Department of Mathematical Sciences, Redeemer’s University, Nigeria.
Professor Dawud A. Agunbiade
Department of Mathematical Sciences, Olabisi Onabanjo University, Ago-Iwoye, Nigeria.
Dr. Pelumi E. Oguntunde
Department of Mathematics, Covenant University, Ota, Nigeria.
Dr. Tolulope F. Adesina
Department of Banking and Finance, Covenant University, Ota, Nigeria.
View Book :- https://stm.bookpi.org/TPMCS-V6/issue/view/6