Factors Influencing Overweight and Obesity in Malawi: A Comparative Analysis of Binary and Multinomial Logistic Regression Models
 
More details
Hide details
1
Research, Clinical Research Education and Management Services, Lilongwe, Malawi
 
2
Department of Engineering, Malawi University of Science and Technology, Thyolo, Malawi
 
3
Department of Mathematical Sciences, University of Malawi, Zomba, Malawi
 
 
Popul. Med. 2026;8(Supplement Supplement 1):
 
ABSTRACT
ABSTRACT:
Obesity and overweight are significant public health concerns, particularly in developing countries like Malawi. These conditions not only increase the risk of chronic non-communicable diseases such as cardiovascular diseases, diabetes, and cancer, but also place a considerable burden on healthcare systems. In recent years, the prevalence of overweight and obesity among Malawian women has risen substantially, driven by socio-economic, lifestyle, and environmental factors. This study investigates the key factors contributing to obesity and overweight in Malawian women, using data from the 2015-16 Malawi Demographic and Health Survey (MDHS). Employing multinomial logistic regression, the analysis identifies the role of variables such as age, wealth index, education, occupation, and type of residence in shaping BMI categories. Our findings reveal that increasing age, higher wealth status, education levels, and urban residency significantly increase the likelihood of being overweight or obese. Despite the growing concern, much of the existing literature overlooks important model diagnostics that ensure robust and reliable results. This study addresses this gap by incorporating model diagnostics, including standardized residuals and Cook’s distance, to assess model fit and handle issues of outliers and influential observations. The results highlight the need for targeted policy interventions, particularly in urban settings, to mitigate the rising rates of obesity and its associated health risks. The study demonstrates the importance of comprehensive statistical analysis and provides valuable insights for policymakers to design effective public health strategies. Data analysis was conducted using Stata version 14.0.
eISSN:2654-1459
Journals System - logo
Scroll to top