Child Labor, Informality, and Poverty: Leveraging Logistic Regression, Indeterminate Likert Scales, and Similarity Measures for Insightful Analysis in Ecuador

Abstract

logistic regression, neutrosophic Likert scales, and similarity measures to deepen the understanding of this social 
issue. The integration of these methodologies allows for a nuanced assessment of the various socio-economic 
factors contributing to child labor. By capturing the uncertainty in human responses, the research highlights the 
complex interplay between poverty, household income, education levels, and labor types on the incidence of child 
labor. Key findings suggest that rural location, the age of the child, and the informal nature of the head of the 
household's work are the most significant predictors of child labor. Notably, parental education appears to have a 
less direct influence. Despite various efforts, including government monetary transfers through programs like the 
BDH, child labor persists, indicating the need for more targeted interventions.The paper proposes future research 
to extend these models to a broader demographic and geographic data set, emphasizing the potential for these 
methods to be applied to a variety of social issues. The development of computational tools to automate 
neutrosophic analysis could greatly benefit large-scale studies, potentially aiding policymakers in designing more 
effective interventions for vulnerable populations. 

DOI: 10.5281/zenodo.10937521