Returns to Education in the United States: A Comparison of OLS and Double Machine Learning Methods

Al Mansor Helal (), Ryotaro Hiraki () and Harry Patrinos
Additional contact information
Al Mansor Helal: University of Arkansas
Ryotaro Hiraki: University of Arkansas

No 18523, IZA Discussion Papers from IZA Network @ LISER

Abstract: This study examines the economic returns to education in the U.S. using 2024 CPS data and compares Ordinary Least Squares (OLS) regression with a Double Machine Learning (DML) framework incorporating models such as random forests, boosted trees, lasso, GAMs, and neural networks (MLP). Results show consistent returns of 8 to 9 percent per additional year of schooling across methods. Simulations reveal that all predictors perform well under linear assumptions if hyperparameters are optimally adjusted, while OLS/Lasso suffer from nonlinearity. Findings suggest that OLS remains robust in low-dimensional, near-linear contexts, offering practical guidance for economists and policymakers balancing model complexity and interpretability in education research.

Keywords: returns to education; machine learning (search for similar items in EconPapers)
JEL-codes: D62 I20 J24 J31 O15 (search for similar items in EconPapers)
Date: 2026-04
New Economics Papers: this item is included in nep-lma
References: Add references at CitEc
Citations:

Downloads: (external link)
https://docs.iza.org/dp18523.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:iza:izadps:dp18523

Access Statistics for this paper

More papers in IZA Discussion Papers from IZA Network @ LISER Contact information at EDIRC.
Bibliographic data for series maintained by Mark Fallak ().