Prediction Gaps as Pathways to Explanation: Rethinking Educational Outcomes through Differences in Model Performance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Garcia-Bernardo, Javier, Jaspers, Eva, Machado, Weverthon, Plach, Samuel, van Leeuwen, Erik Jan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911027805814784
author Garcia-Bernardo, Javier
Jaspers, Eva
Machado, Weverthon
Plach, Samuel
van Leeuwen, Erik Jan
author_facet Garcia-Bernardo, Javier
Jaspers, Eva
Machado, Weverthon
Plach, Samuel
van Leeuwen, Erik Jan
contents Social contexts -- such as families, schools, and neighborhoods -- shape life outcomes. The key question is not simply whether they matter, but rather for whom and under what conditions. Here, we argue that prediction gaps -- differences in predictive performance between statistical models of varying complexity -- offer a pathway for identifying surprising empirical patterns (i.e., not captured by simpler models) which highlight where theories succeed or fall short. Using population-scale administrative data from the Netherlands, we compare logistic regression, gradient boosting, and graph neural networks to predict university completion using early-life social contexts. Overall, prediction gaps are small, suggesting that previously identified indicators, particularly parental status, capture most measurable variation in educational attainment. However, gaps are larger for girls growing up without fathers -- suggesting that the effects of social context for these groups go beyond simple models in line with sociological theory. Our paper shows the potential of prediction methods to support sociological explanation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22993
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prediction Gaps as Pathways to Explanation: Rethinking Educational Outcomes through Differences in Model Performance
Garcia-Bernardo, Javier
Jaspers, Eva
Machado, Weverthon
Plach, Samuel
van Leeuwen, Erik Jan
Social and Information Networks
Social contexts -- such as families, schools, and neighborhoods -- shape life outcomes. The key question is not simply whether they matter, but rather for whom and under what conditions. Here, we argue that prediction gaps -- differences in predictive performance between statistical models of varying complexity -- offer a pathway for identifying surprising empirical patterns (i.e., not captured by simpler models) which highlight where theories succeed or fall short. Using population-scale administrative data from the Netherlands, we compare logistic regression, gradient boosting, and graph neural networks to predict university completion using early-life social contexts. Overall, prediction gaps are small, suggesting that previously identified indicators, particularly parental status, capture most measurable variation in educational attainment. However, gaps are larger for girls growing up without fathers -- suggesting that the effects of social context for these groups go beyond simple models in line with sociological theory. Our paper shows the potential of prediction methods to support sociological explanation.
title Prediction Gaps as Pathways to Explanation: Rethinking Educational Outcomes through Differences in Model Performance
topic Social and Information Networks
url https://arxiv.org/abs/2506.22993