Using Logistic Regression Model to Study the Most Important Factors Which Affects Diabetes for The Elderly in The City of Hilla / 2019

Abstract

Abstract The aim of this paper is to study the most important factors affecting diabetes using the logistic regression method and to conduct all tests for this method (Hosmer and Lemeshow test, Omnibus tests of model coefficients, …etc.). The randomized sample included (150) people among the elderly in Al-Hilla city, the research included focusing on (14) independent variables and most of these variables were found to have significance, effect and contribution to the logistic regression - binary response (not sick(0), sick(1)) model are (4) variables (cigarette smoking, exercise, vitamin (D), blood pressure), Which affects diabetes, and the rest of the variables have no significance or effect. The classification of observations using logistic regression-binary response model was accurate, as the overall correct classification rate was (92.7%) while the overall wrong classification rate was (7.3%).