Final Exam - James Peng
Committee: Peter Gilbert (chair), Pamela Shaw, Linbo Wang, Amy Willis, Thomas Richardson, Lillian Cohn (GSR)
Presentation: Statistical methods for analyzing deep sequencing data in HIV-1 prevention trial sieve analyses
Abstract: Understanding how vaccines perform against different pathogen genotypes is crucial for developing effective prevention strategies, particularly for highly genetically diverse pathogens like human immunodeficiency virus-1 (HIV-1). Sieve analysis is a statistical framework used to determine whether a vaccine selectively prevents infection by certain genotypes while allowing breakthrough of other genotypes that evade immune responses. Traditionally, these analyses are conducted with a single sequence available per individual acquiring the pathogen. However, modern deep sequencing technology can provide detailed characterization of within-host viral diversity by capturing up to hundreds of pathogen sequences per person.
In this dissertation, we develop statistical methods for…
Event interval: Single day event. Campus location: Hans Rosling Center for Population Health (HRC). Online Meeting Link: https://washington.zoom.us/j/91084887744. Campus room: HRC 370. Accessibility Contact: Deb Nelson, nelsod6@uw.edu, 206-685-9323. Event Types: Academics.
Tuesday, August 11, 2026, 2:00 PM – 4:00 PM.
Final Exam - Taek Son
Committee: Kwun Chuen Gary Chan (co-chair); Eardi Lila (co-chair); Ting Ye, Abraham Flaxman (GSR)
Title: Dimension Reduction and representation Learning for Improved Estimation of Causal Parameters
Abstract: High-dimensional observational data, including electronic health records and omics measurements, create substantial challenges for causal inference. The growing complexity of such data can hinder both estimation and interpretation. This dissertation focuses on heterogeneous treatment effects, individualized treatment regimes, and mediation analysis, and develops dimension-reduction and representation-learning methods tailored to their causal targets to facilitate inference.
First, we propose a sufficient dimension-reduction method that directly targets treatment effect heterogeneity by identifying a low-dimensional linear subspace of the covariates. Combined with kernel-based covariate-balancing, this representation facilitates the estimation of optimal individualized treatment regimes through…
Event interval: Single day event. Campus location: Hans Rosling Center for Population Health (HRC). Online Meeting Link: https://washington.zoom.us/j/7580402955. Campus room: HRC 370. Accessibility Contact: Deb Nelson, nelsod6@uw.edu, 206-685-9323. Event Types: Academics.
Friday, August 14, 2026, 9:00 AM – 11:00 AM.
Final Exam - Jaewon Lim
Committee: Alex Luedtke (chair), Marco Carone, Ting Ye, Abraham Flaxman (GSR)
Presentation: Orthogonal statistical learning and inference for function-valued parameters with heterogeneous data sources
Abstract: There is a growing literature on estimating function-valued parameters by combining semiparametric efficiency theory and statistical learning. A second trend is the integration of multiple, partially overlapping data sources through data fusion and two-phase sampling. This dissertation develops theory and methodology at the intersection of these two directions.
In the first aim, I study data fusion for estimating causal dose-response functions, where a single dataset does not contain enough observations at every exposure level. I introduce a data fusion framework leveraging partially aligned sources, and construct a Neyman-orthogonal loss robust to nuisance estimation error. I develop two estimation algorithms, a general two-stage procedure and a closed-form kernel ridge regression estimator and…
Event interval: Single day event. Campus location: Hans Rosling Center for Population Health (HRC). Online Meeting Link: https://washington.zoom.us/j/92798528454. Campus room: HRC 375. Accessibility Contact: Deb Nelson, nelsod6@uw.edu, 206-685-9323. Event Types: Academics.
Tuesday, August 18, 2026, 10:30 AM – 12:30 PM.