Information Systems Faculty Publications and Presentations

Methodology to combine theoretical knowledge with a data-driven probabilistic graphical model

Document Type

Article

Publication Date

7-2021

Abstract

This study presents an analytic inference methodology using probabilistic modeling that provides faster decision-making and a better understanding of complex relations. Two educational psychology models (i.e., the MUSIC Model of Motivation and the domain identification model) were coupled with a data-driven Probabilistic Graphical Model to provide a top-down and bottom-up combination for reasoning. Using survey data from middle school students, Bayesian Network models captured the probabilistic interactions between students’ perceptions of their science class, their identification with science, and their science career goals. Complex/non-linear relationships among these variables revealed that students’ perceptions of their science class (i.e., eMpowerment, Usefulness, Success, Interest, and Caring) were significant predictors of their science-related career goals. These findings provide validity evidence for using the MUSIC and domain identification models and provide educators and school administrators with a web-based simulator to estimate the effect of students’ science class perceptions on their science identification and career goals.

Comments

© Operational Research Society 2021.

NOT OPEN ACCESS.

Publication Title

Journal of Business Analytics

DOI

10.1080/2573234X.2021.1937351

Link to Full Text

Share

COinS