ORIGINAL RESEARCH article
Front. Educ.
Sec. STEM Education
This article is part of the Research TopicBridging Barriers: Technology Integration in Mathematics EducationView all 7 articles
Advancing Textbook Evaluation with Debiased Machine Learning: A Theoretical and Empirical Approach
Provisionally accepted
- 1Texas A&M University, College Station, United States
- 2Wayne State University, Detroit, United States
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Textbooks play a crucial role in shaping student achievement, yet traditional methods of evaluating their effectiveness often rely on linear models that impose restrictive assumptions. This study introduces Double/Debiased Machine Learning (DML) as a robust alternative for assessing textbook impact. By leveraging nonparametric modeling, DML provides more precise causal estimates compared to conventional Ordinary Least Squares (OLS) regression and Kernel matching techniques. We mathematically derive the advantages of DML and apply it to an existing dataset from a large-scale elementary school math curriculum study. Our findings demonstrate that DML enhances the accuracy and efficiency of textbook effect estimation, offering new insights into educational material selection. This research contributes to the broader understanding of intelligence by refining the methodological tools used to measure learning outcomes.
Keywords: California Math, Causal, DML, Estimation, Nonparametric modeling
Received: 14 May 2025; Accepted: 08 Dec 2025.
Copyright: © 2025 Fang and Bian. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Yong Bian
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.