Understanding U.S. Rural Students’ Mathematics Performance: A Transfer Learning Approach on PISA 2022

• In Event: AERA Poster Session Friday 9:45am
  In Poster Session: Student Learning in Mathematics Education

Abstract

This study aims to examine rural students’ math performance, focusing on identifying the key factors that influence their success in math. Using the PISA 2022 U.S. dataset, kernel density estimation and Kolmogorov-Smirnov test results reveal significant math performance gaps between rural and urban students. To address the challenge of small rural sample sizes, we employed a transfer learning method to leverage information from related urban data to improve model performance. Results indicate that school-level support structures contribute substantially to the observed gaps in students’ math performance across different regions. The findings show how structural and systemic inequities, rather than individual student abilities alone, play a central role in shaping math achievement outcomes. The implications of these findings are discussed.

Authors

• Li Zhu, University of Iowa

• Hyesun You, University of Iowa

• Zhenhan Fang, University of Iowa

• Dae S. Hong, University of Iowa