27 October، 2022

Discussion of a master’s thesis in the College of Computer Science and Mathematics

Discussion of a master’s thesis in the College of Computer Science and Mathematics – Department of Statistics and Informaticsentitled:(Count Data Modeling with Overdispersion and Underdispersion Issues)Master’s thesis by student Mohammed Khalid Mohammed Nori, under the supervision of Professor Dr. Zakariya Yahya Nori. as discussed in the discussion room at the Faculty of Computer Science and Mathematics at the University of Mosul on Thursday27/10/2022This study focuses onRegression analysis is great of interest in several studies. The efficiency of the Poisson regression model is depending on the equalization of the mean and variance of the data. However, the model may contain the overdispersion or underdispersion problemwhich affects the interpreting of the results.The study touched the Monte-Carlo simulation study is used depending on several factors, such as the dispersion factor and the sample size. In terms of prediction accuracy, simulation results demonstrated that the negative binomial regression model has better results comparing with other regression model when the dispersion factor exist. Furthermore, generalized Poisson regression model yields better performance compared to other regression models when the underdispersion is exist. In addition, the result of the real data application, which is related to the patients with chronic renal insufficiency.This study aims to model the count data under the overdispersion or underdispersion problem.The discussion committee consists of

Prof. Dr. Ahmed Shaker Metwally

Assis. Prof. Dr. Bashar Abdel Aziz Majid

Lecturer. Dr. Zaid Tariq Saleh

Prof. Dr. Zakariya Yahya Nori

Share

Share

Go to Top