Seminar: The Unlikely Methodologist

The Unlikely Methodologist: A hodge-podge talk about my research and lessons learned along the way

Dr. Jaime Speiser, Assistant Professor of Biostatistics and Data Science at Wake Forest University School of Medicine

October 11; 11am – 12pm in Carswell 101

Abstract: In this seminar, I will talk about machine learning methods I have developed for clustered and longitudinal data. The family of methods is called Binary Mixed Model (BiMM). There are decision tree and random forest versions (BiMM tree and BiMM forest). Recently, I have added variable selection, and I am currently working on missing data imputation (BiMMputation). Part of the talk will focus on benchmarking studies for comparing methods. I will share my personal journey for this work and some lessons I learned along the way. I consider myself an Unlikely Methodologist because I am not particularly good at statistical theory or programming. Nonetheless, I have forged a path in methodology development and have been surprised at how much I like doing this work.

Due to the health needs of some of our attendees and Jaime’s request, we ask that all attendees wear a mask and refrain from wearing perfume, cologne, or other scented products.