Paradigm Wars II: The Ongoing Struggle Between Machine Learning and Classical Statistical Modeling

• In Event: Educational Research in Transition: From Classical Methods to Machine Learning

Abstract

In the late 1980s, Nate Gage (1989) wrote about the ongoing debate around the possibility of objectivity in educational research and warned that the end would mean that “one paradigm grinds the others into dust” (p. 10). Today, we are on the precipice of a looming paradigm war: that between classical research methodology and modern machine learning. This paper will discuss the ongoing debate by looking at the rise and development of machine learning models, their inherent problems, and the implications for future educational research.

Authors

• J. Kyle Roberts, Southern Methodist University

• Ellen Taylor, Southern Methodist University