Evaluating Longitudinal Change in STEM Identity: Explanatory Rasch Modeling

• In Event: AER Roundtable Session Friday 1:45 pm - Gold 4
  In Roundtable Session: Innovations in Item Response Theory for Modeling Student Performance and Growth

Abstract

This study evaluated longitudinal change in STEM identity among youth using explanatory Rasch modeling. Participants (N = 34) completed a 12-item STEM-Identity scale at three points during a weeklong STEM camp. Rasch models assessed psychometric quality, while five logistic mixed-effects models examined growth over time. Although item endorsement increased slightly, the fixed effects of time were not statistically significant. Model 2, which included random slopes for persons, provided the best fit. The scale demonstrated stable item functioning and adequate reliability. Findings highlight the value of explanatory Rasch models for capturing nuanced identity development and stress the need for sustained interventions to support meaningful growth in STEM identity.

Authors

• Justice Dadzie, University of Alabama

• Daniel O. Oyeniran, University of Alabama

• Joni M. Lakin, University of Alabama