Matthew Wigginton Bhagat-Conway
Matthew Bhagat-Conway is an Assistant Professor in the Department of City and Regional Planning. His research interests are in travel behavior, urban transportation, and statistical methods for transportation data analysis. He is also jointly appointed in the Odum Institute for Research in the Social Sciences, where he is available to assist researchers with statistics and data analysis.
Dr. Bhagat-Conway has a PhD and MA in Geography from Arizona State University, and a BA in Geography from the University of California, Santa Barbara. Prior to graduate school, he was a software developer and project manager for Conveyal, a public transport planning consulting firm, and a fellow in the Data Science for Social Good fellowship at the University of Chicago.
Random utility models are widely used in social science. While most statistical software, including Julia, has some facilities for estimating multinomial logit models, more advanced models such as mixed logit models and models with different utility functions for different outcomes generally require specific choice modeling software. This presentation describes a new package, DiscreteChoiceModels.jl, which provides flexible and high-performance multinomial and forthcoming mixed logit estimation.