College of Computer Science and Mathematics

Discussion of the master’s thesis in the College of Computer Science and Mathematics -Department of Statistics and Informatics Department entitled:

A proposed method to reduce the dimensions of variables in logistic regression

It was discussed in the College of Computer Science and Mathematics discussion hall at the University of Mosul on Thursday, 2/27/2025.

Master’s thesis by  Suhaib Bashar Hameed

supervised by Dr. Mahmood Mohammed Taher

The thesis addresses the use of cluster analysis to reduce variables in a logistic regression model, with the aim of identifying the main factors affecting kidney failure. The study was applied to data taken from Ibn Sina Hospital, including 142 patients.

The study addressed The study showed the importance of using cluster analysis to group variables and improve the accuracy of statistical models. Independent variables such as age, gender, urea and creatinine ratio were also analyzed, and their effect was tested using logistic regression models. The study concluded with a statistical model capable of predicting the probability of developing kidney failure based on the specified factors.

The study aims to identify the independent variables affecting kidney failure by applying a proposed method based on grouping independent variables into clusters to apply binary logistic regression and build a model to estimate the probability of developing this disease.

The discussion committee consists of

Dr. Rikan Abdul Aziz Ahmed (Chairman)

Dr. Alaa Abdel Sattar Daoud  (member)

Dr. Mahmood Mohammed Taher (member and supervisor)