ALT Join us for the Biostatistics & Epidemiology Research Showcase. Come hear our brilliant presenters share their cutting-edge research in fast-paced, engaging sessions. Check out the incredible lineup of speakers and their titles below! Date: Friday, May 1, 2026 Time: 2:30 PM - 4:30 PM Location: Berkeley Way West, 1st Floor | Room 1102 Presenters: Kaitlyn Lee - Improving Precision through Covariate Adjustment in RCTs with Binary Outcomes Nick Williams - Improving Reproducibility by Controlling Random Seed Stability in Machine Learning Based Estimation via Bagging John Halifax - Estimating Causal Effects of Community Drivers of Individual Health in the Presence of Community-Specific Confounding in Large Data Settings Alissa Gordon - The Average Mixed Derivative: A Nonparametric Framework of Interactivity Joy Nakato - Choices and Consequences of Alternative Estimands in Time-to-event Safety Analyses Noel Pimentel - MASH Placebo-Arm Database Project

ALT Calling all UC Berkeley Biostat and Epi graduate students! Got exciting research to share? Join us for the Biostat and Epi Research Showcase—your chance to present to faculty, peers, and special guests! Visit the link in our bio for full details on presentation formats 🔗

ALT We’re excited to host two insightful talks from Tianyue Zhou and Toru Shirakawa next week as part of our CTML Seminar Series on Wed, March 11 from 12PM-1PM at BWW, 5th Floor, Room 5401. Join us for an engaging session–we look forward to seeing you there!

ALT Title: "Generating High-Quality Real-World Evidence at Scale with a Causal Roadmap Copilot" Abstract: In this talk, I will discuss why we are at an unprecedented moment for generating rigorous real-world evidence at scale. I will then introduce our vision for what we aim to build—the Causal Roadmap Copilot—and share updates on our current development progress. I will conclude with key next steps.

ALT Title: "Survival Deep LTMLE with an Application to Longitudinal Chronic Disease Management" Abstract: Chronic conditions such as hypertension, diabetes mellitus, obesity, and dyslipidemia require sustained long-term management to prevent serious complications and mortality. Evaluating the causal effects of sustained treatment strategies on long-term survival outcomes is therefore a central challenge in precision health. We developed an extension of Deep LTMLE which estimates counterfactual survival curves via temporal-difference learning. In this talk, I will introduce the model and demonstrate its application to real-world longitudinal health data.

ALT Don't miss the next session of the CTML Seminar Series on March 4th, where CTML GSR Alissa Gordon will discuss "Average Mixed Derivative: A Nonparametric Framework of Interactivity." This talk will take place from 12:00PM-1:00PM at Berkeley Way West, 5th Floor, Room 5401.

ALT There are many ways that multiple theoretically intervenable variables can synergize or antagonize to affect an outcome. We review several definitions of "interaction" and propose a new estimand called the average mixed derivative (AMD) that captures a scalar notion of interactivity within a nonparametric framework. We identify the AMD under standard causal assumptions and develop regression, weighting, and doubly-robust type estimators, focusing on continuous exposures and outcomes.

ALT Support the Future of Public Health Innovation—Donate to CTML for UC Berkeley’s Big Give on March 12th! With over 15 Graduate Student Researchers, CTML is leading discoveries that improve health outcomes locally and globally. Learn more 👉 https://ctml.berkeley.edu/join-us-big-give-2026