Using Multinomial Logistic Regression to Identify Key Factors Affecting the Standard of Living in Sinnar, Sudan
DOI:
https://doi.org/10.59992/IJFAES.2025.v4n4p11الكلمات المفتاحية:
Multinomial Logistic Regression، Household Living Standards، Economic Factors، SPSS، Sinnar State، Sudanالملخص
This study aims to identify and analyze the key determinants of household living standards in Sinnar State, Sudan, by using Multinomial Logistic Regression (MLR) to assess the impact of economic, demographic, and health-related factors. Given the disparities in living standards across the region, understanding the underlying causes is essential for guiding policy interventions. The study classifies households into three categories—high, middle, and low standard of living—based on variables such as income, education, access to healthcare, household size, and occupation. Primary data were collected through a detailed questionnaire, and secondary data were used to complement the findings. The sampling method involved a two-stage cluster sampling approach, resulting in a sample size of 800 households, and data analysis was conducted using SPSS software.
The study reveals that significant predictors of living standards include monthly household income, place of residence (urban vs. rural), occupation type, ownership of assets (such as cars and smart screens), and access to healthcare. The MLR model showed a classification accuracy of 84.1%, with higher accuracy for low-standard households (89.5%) compared to middle (81.2%) and high-standard households (75.4%). Key factors such as professional occupation and sufficient income were found to increase the likelihood of higher living standards, while rural residence and insufficient income were linked to lower living standards.
The research highlights the importance of these determinants for informed policymaking and the need for targeted interventions to improve living standards. Recommendations for future studies include expanding the set of variables considered and applying advanced statistical techniques for better classification accuracy. Additionally, the study calls for job creation initiatives to improve income levels and reduce socio-economic disparities. This research provides a understanding the socio-economic factors that influence living standards in Sinnar State.
المراجع
1. Abdelmonem, A. & May, S. (2012). Practical multivariate analysis (5th ed). Taylor & Francis Group, LLC. https://doi.org/978-1-4665-0324-3
2. Abdelmonem, A., May, S., Donatello, R. A., & Clark, V. A. (2020). Practical multivariate analysis (6th ed). Taylor & Francis Group, LLC. https://doi.org/978-1-138-70222-6
3. Izenman, A. J. (2008). Modern multivariate statistical techniques: Regression, classification, and manifold learning. Springer-Verlag New York. https://doi.org/10.1007/978-0-387-78185-8
4. Fadl Al-Mawla, A. A. (2015). Comparison of discriminant analysis, binary logistic regression, and neural network models in observation classification, Sudan (Unpublished master’s thesis). Khartoum University of Science and Technology.
5. Rencher, A. C. (2002). Methods applied multivariate analysis. Springer-Verlag New York, Inc.
6. Hosmer, D. W., & Lemeshow, S. (2000). Applied logistic regression (3rd ed). John Wiley & Sons, Inc.
7. Everitt, B., & Hothorn, T. (2011). An introduction to applied multivariate analysis with R. Springer, Verlag New York. https://doi.org/10.1007/978-1-4419-6358-4
8. Czepiel, S. A. (2002). Maximum likelihood estimation of logistic regression models: Theory and implementation. Retrieved from http://czep.net
9. Garson, G. D. (2014). Logistic regression binary and multinomial. Statistical Associates Publishing.
10. Hilbe, J. M. (2009). Logistic regression models. Jet Propulsion Laboratory, California Institute of Technology, Taylor & Francis Group, LLC.
11. Johnson, R. A., & Wichern, D. W. (2007). Applied multivariate statistical analysis (6th ed.). Pearson Prentice Hall.
12. Ho, R. (2006). Handbook of univariate and multivariate data analysis and interpretation with SPSS. Taylor & Francis Group, LLC.
13. Karl, W., & Simar, L. (2007). Applied multivariate statistical analysis. Springer, Berlin Heidelberg New York.
14. Ahmad, Z., & Ejaz, Z. (2011). Classification of households with respect to poverty by using cluster analysis. Proceedings of ICCS-11, Lahore, Pakistan.
