Title: Using Machine Learning to Predict PARCC Algebra I Scores
Date and Time: Friday, May 19, 2023 - 12 noon to 1 p.m. Eastern
Location: May Research Series Zoom
RSVP: Jamese Dixon-Bobbitt via email: jamese.dixon-bobbitt@maryland.gov
Presentation Abstract:
Machine learning is a useful tool for data prediction and has been used in a variety of disciplines, including education. This project examined the extent to which machine learning algorithms could be used with MLDS data through an exploratory study to predict high-stakes assessment scores in Algebra. Second, this project examined whether these scores could be used as predictors in future analyses predicting college enrollment.
Finally, this project examined the extent to which scores were equitably predicted across various subgroups. A discussion will focus on the strengths and limitations of applying machine learning algorithms to predict test scores.
Presenters: Dr. Tracy Sweet, Ms. Brennan Register, Ms. Ashani Jayasekera, MLDS Research Branch and University of Maryland College Park
About the Presenters Tracy Sweet is an Associate Professor in the Quantitative Methodology: Measurement and Statistics program in the Department of Human Development and Quantitative Methodology at the University of Maryland College Park. She is also the Associate Director of Research for MLDS Center Research branch. Her research focuses on various data science methods such as machine learning and network analysis as well as equity in quantitative methods.
Brennan Register is a fourth-year Ph.D. student in the Quantitative
Methodology: Measurement and Statistics program at The University of
Maryland, College Park. She joined the University of Maryland after
obtaining a Master's in Statistics from the University of Pittsburgh. Her
research focuses on investigating the performance of multilevel and
standard prediction algorithms on large-scale educational datasets. She
has been working with the MLDS research group since the fall of 2019.
Ashani Jayasekera is a first-year doctoral student in the Quantitative Methodology: Measurement and Statistics program at the University of Maryland College Park. She earned an MS in Measurement, Statistics & Evaluation from the University of Maryland College Park and a BS in Mathematics from the University of Maryland Baltimore County. Her research interests are in machine learning, natural language processing, the analysis of complex data structures, as well as multilevel modeling. Recent research projects include work on the utilization of propensity scores to provide measures of school quality, the impacts of missing data on social network models, and the evaluation of machine learning-aided tools for the systematic review process.
______________________________________________________________________________