Dr. Yixiao Dong, an Assistant Professor of Quantitative Methods in the Department of Education here at UCSB, will be speaking about "Is a Less Wrong Model Always More Useful? Exploring Optimal Measurement Solutions Using Meta-Heuristic Algorithms" on Wednesday, October 21st, 2026 in HSSB 1173 from 3:30 - 4:30pm.
Abstract:
In recent years, AI-derived techniques have been adopted in psychological and behavioral science research, including measure development. Metaheuristic algorithms such as Ant Colony Optimization (ACO) are among those techniques that have been integrated into the structural equation modeling framework to search for optimal (or near-optimal) models and measurement solutions. This talk introduces ACO and discusses whether its solutions are indeed optimal and whether ACO-optimized measurement models are always more psychologically useful than conventional ones developed by human psychometricians.
Bio:
Dr. Yixiao Dong is an Assistant Professor of Quantitative Methods in the department of Education. His research focuses on the development and application of advanced quantitative methodologies to optimize educational and psychological processes and outcomes. Prior to his academic journey, he taught young children at a charter school with a fully inclusive program in Denver.