Researcher: Moloko Legodi, University of Limpopo
Supervisor: TBA
A report by World Health Organization support that cancer is the global health problem, responsible for roughly 10 million deaths in 2020. The goal of this research is to look at factors that may lead to death in people with cancer. The goals of this study is to (a) analyze the data using the Poisson regression model, Negative Binomial regression, and Zero Inflated Poisson to see which model best fit the data, and (b) look for factors that lead to death in cancer patients. Data from Statistics South Africa (StatsSA) on causes of death was analyzed, and the study looked at 22441 people who died from cancer as reported by the Department of Home Affairs in South Africa in 2015 (SA). Descriptive statistics and model fitting were used to analyze the data. The data was analyzed first using the Poisson regression model, then an detection of over dispersion in count variable Negative Binomial regression, and ZIP, where negative binomial was the best model to fit the data. The model fitted from Negative binomial revealed that the age group, place of death, province of death, and smoking status have a significant contribution on the number of cancer deaths at a 5\% significant level, while the variable gender was in significant to the model. Cancer patients should use nursery homes in the future so that they can be closely monitored while undergoing treatment. The country’s health department should strengthen cancer education for youth for the sake of the country’s cancer future state, as youth are the country’s future.
