Bentley University
ChatGPT vs. Machine Learning: Assessing the Efficacy and Accuracy of Large Language Models for Automated Essay Scoring
Automated Essay Scoring (AES) is a critical tool in education that aims to enhance the efficiency and objectivity of educational assessments. Recent advancements in Large Language Models (LLMs), such as ChatGPT, have sparked interest in their potential for AES. However, comprehensive comparisons… more →
Beg to DIFfer: Resolving Statistical Complications of Intersectional DIF Analyses
Modern test developers conduct differential item functioning (DIF) analyses to ensure fairness in educational and psychological testing. To address previously unrecognized biases, researchers have recently demonstrated the importance of conducting intersectional DIF analyses that attend to the… more →
The Effect of College Entrance Exam Policies on Test Preparation and Tutoring Services
Multiple studies suggest that policies mandating college entrance exams can have positive impacts on college outcomes, especially for students who would otherwise not sit for the exam. Less understood is how families react to this increased competition for college admissions. Our study estimates… more →
The Causal Impact of Charter Schools on Private Tutoring Prevalence
Greater school choice leads to lower demand for private tutoring according to various international studies, but this has not been explicitly tested for the U.S. context. To estimate the causal effect of charter school appearances on neighboring private tutoring prevalence, we employ a… more →
Online Tutoring by College Volunteers: Experimental Evidence from a Pilot Program
A substantial body of experimental evidence demonstrates that in-person tutoring programs can have large impacts on K-12 student achievement. However, such programs typically are costly and constrained by a limited local supply of tutors. In partnership with CovEducation (CovEd), we conduct a… more →
Bridging human and machine scoring in experimental assessments of writing: tools, tips, and lessons learned from a field trial in education
In a randomized trial that collects text as an outcome, traditional approaches for assessing treatment impact require that each document first be manually coded for constructs of interest by human raters. An impact analysis can then be conducted to compare treatment and control groups, using the… more →