Answers are grounded in this paper and cite their sources.
This study focuses on the determinants of educational lag among children in Mexico, with a particular emphasis on households headed by working single mothers. Drawing on the 2022 ENIGH dataset and a multidimensional framework, the research integrates econometric methods (LASSO and probit) with machine learning (SVM) to estimate the probability of educational lag. Results show that age, maternal education, and household deprivations significantly increase the likelihood of educational lag. Conversely, speaking an Indigenous language and maternal employment are associated with reduced probability. While the probit and LASSO models effectively identify at-risk individuals, the SVM model offers high specificity, but underestimates positive cases. Findings highlight the importance of gender-sensitive policies and structural support for single-mother households to mitigate educational disparities and break intergenerational cycles of poverty.
No takes yet. Share an insight, caveat, or question.
Andrea Fastlicht Perelman (2025) studied this question.
Synapse has enriched 9 related papers. Consider them for comparative context: