Modeling Life Expectancy Through Governance and Socioeconomic Factors: A Bayesian Network Analysis

Modeling Life Expectancy Through Governance and Socioeconomic Factors: A Bayesian Network Analysis

ES评分 0

DOI 10.20900/jsr20260068
刊名
JSR
年,卷(期) 2026, 8(3)
作者
作者单位

Program of Industrial Engineering, Universidad del Atlántico, Barranquilla 081007, ColombiaProgram of Industrial Engineering, Universidad del Magdalena, Santa Marta 470004, ColombiaStatistical and Quantitative Methods Research Group (GEMC), Universidad del Magdalena, Santa Marta 470004, Colombia

摘要
Life expectancy is a central indicator of population well-being and sustainable development, but it is often analysed using linear econometric frameworks that emphasise isolated marginal associations. This study applies Bayesian network modelling to examine conditional dependencies among gross national income per capita, governance quality, logistics performance, and life expectancy at birth across 137 countries. Using a score-based hill-climbing algorithm, bootstrap validation, mutual information, and conditional probability analysis, the study identifies stable probabilistic configurations associated with different life expectancy levels. The results indicate that income presents the strongest conditional association with life expectancy, while governance quality is associated with configurations in which economic resources are more consistently linked to higher longevity outcomes. Additional benchmark regression models and sensitivity analyses are used to assess the robustness of the observed patterns. Because the study is based on cross-sectional observational data, the results should not be interpreted as causal effects. Instead, the paper’s contribution lies in providing a complementary probabilistic framework for exploring how socioeconomic and institutional indicators jointly characterise global differences in life expectancy.
Abstract
Life expectancy is a central indicator of population well-being and sustainable development, but it is often analysed using linear econometric frameworks that emphasise isolated marginal associations. This study applies Bayesian network modelling to examine conditional dependencies among gross national income per capita, governance quality, logistics performance, and life expectancy at birth across 137 countries. Using a score-based hill-climbing algorithm, bootstrap validation, mutual information, and conditional probability analysis, the study identifies stable probabilistic configurations associated with different life expectancy levels. The results indicate that income presents the strongest conditional association with life expectancy, while governance quality is associated with configurations in which economic resources are more consistently linked to higher longevity outcomes. Additional benchmark regression models and sensitivity analyses are used to assess the robustness of the observed patterns. Because the study is based on cross-sectional observational data, the results should not be interpreted as causal effects. Instead, the paper’s contribution lies in providing a complementary probabilistic framework for exploring how socioeconomic and institutional indicators jointly characterise global differences in life expectancy.
关键词
life expectancy; Bayesian networks; governance quality; socioeconomic determinants; sustainable development
KeyWord
life expectancy; Bayesian networks; governance quality; socioeconomic determinants; sustainable development
基金项目
页码 -
  • 参考文献
  • 相关文献
  • 引用本文

Adel Mendoza-Mendoza, Delimiro Visbal-Cadavid, Enrique Delahoz-Domínguez. Modeling Life Expectancy Through Governance and Socioeconomic Factors: A Bayesian Network Analysis [J]. Journal of Sustainability Research. 2026; 8; (3). - .

  • 文献评论

相关学者

相关机构