Using the Multiple Ordinal Logistic Regression Model to Identify the Most Important Demographic and Environmental Factors Affecting the Incidence of Cancer Among Children in Basra Governorate

Authors

  • Shereen A. Hussain
  • Saad K. Hamza

DOI:

https://doi.org/10.55562/jrucs.v54i1.601

Keywords:

Regression models, multiple logistic regression, demographic and environmental factors, childhood cancers

Abstract

High flexibility characterizes logistic regression, which is regarded as one of the significant statistical techniques for estimating the probability of an event occurring by matching data and information on the logistic curve, as it usually works to describe the nature of the relationship between the two response variables, which are usually categorical or ordinal and a group of independent variables. Because of its nominal nature, the logistic regression model expresses a special case of the normal regression model. Depending on the response variable, there are several types of logistic regression, including binary logistic regression, which is typically used when the response variable has two values (0,1), as well as multi-response (multinomial logistic) when the response variable has more than two categories, as for ordinal logistic regression, as it is used in the case of the response variable, it is ordinal. This study used rank- order logistic regression models to identify the most significant environmental and demographic factors affecting the incidence of cancer in children in the Basra Governorate. The response variable was the severity of the injury, starting from no injury to a severe injury. We arrived at the variables that affect the determination of infection in a child at the 2019 Children's Specialist Hospital in Basra. These variables include sex, age, residence location, father’s occupation, father's educational attainment, standard of living, father's type of work, heredity, housing location in relation to oil fields, proximity to radiation-contaminated areas, cancer type, treatment, type of housing, and duration of injury. The researcher reached the conclusion that there are several variables that have a direct impact on the incidence of cancer, including the location of residence, particularly if it is close to oil wells and refineries, the father’s work, particularly if the family head is employed, and the availability of treatment, where the significance was lower than 0.05, which has a significant effect on the incidence of the disease.

Downloads

Download data is not yet available.

Downloads

Published

2024-01-14

How to Cite

Using the Multiple Ordinal Logistic Regression Model to Identify the Most Important Demographic and Environmental Factors Affecting the Incidence of Cancer Among Children in Basra Governorate. (2024). Journal of Al-Rafidain University College For Sciences ( Print ISSN: 1681-6870 ,Online ISSN: 2790-2293 ), 54(1), 309-318. https://doi.org/10.55562/jrucs.v54i1.601