Gabriel Durham's Homepage

Welcome to my homepage! I am currently a PhD student in the Department of Statistics at the University of Michigan.  I have the fortune of working with the fantastic researchers in d3center ("d3c") within the Institute for Social Research, studying statistical concerns regarding adaptive interventions. 

My primary focus at d3c has been my work with Danny Almirall on the analysis of clustered sequential, multiple assignment, randomized trials (SMARTs). Our current work concerns primary aim methods for longitudinal data analyses in clustered SMARTs, and we are excited to get these tools in the hands of applied researchers to help them create better-informed adaptive interventions! Along with our current work, I am excited about the directions in which the field is moving (e.g., analyses of multi-level adaptive interventions, post-selection inference methodologies in SMART analyses, and examining sequentially randomized trial data under treatment effect interference). Lastly, my research also focuses on statistical issues that arise when ML/GenAI models are embedded into broader processes. These can pop up in situations like using LLMs for sequential text interventions, and induce exciting collaborations between cutting edge advances in ML and classical methods from causal inference and reinforcement learning!

Before coming to Michigan, I analyzed social and economic policy at Abt Associates. While my statistical research has (thus far) mainly involved applications of causal inference in policy interventions, I am generally interested in statistical questions motivated by real world problems that can help real world people! In particular, I enjoy working on problems at the intersection of causal inference and machine learning.

GitHub