Statistics Seminar Series: David Benkeser, Ph.D.

About this event

Please join us for the Statistics Seminar Series with speaker David Benkeser, Ph.D., Associate Professor of Biostatistics and Bioinformatics at the Emory University Rollins School of Public Health.Talk Title: Causal Vaccine Effects on Post-infection Outcomes in the Naturally InfectedAbstract: Understanding vaccine effects on post-infection outcomes is critical for evaluating the full value proposition of a vaccine. However, defining appropriate causal effects on such outcomes can be challenging. We propose causal estimands for post-infection outcomes in the Naturally Infected subpopulation consisting of individuals who would be infected in absence of vaccine. We discuss partial identification using bounds and point identification and estimation using semi-parametric efficient one-step estimators with robustness properties under inconsistent nuisance parameter estimation. We further show under what conditions the same identification functional can be interpreted as targeting an effect among individuals exposed to a sufficiently infectious dose of the pathogen, thereby avoiding direct reliance on cross-world parameters and fundamentally untestable causal assumptions. We illustrate the method using an analysis of a rotavirus vaccine trial and simulation studies aimed to guide the design of Shigella vaccine trials. This seminar will be held in-person and via Zoom. If you are unable to attend the seminar and would like the recording, please email Lauren Spencer (lauren_spencer@brown.edu (mailto:lauren_spencer@brown.edu)). *Lunch will be provided on a first-come basis.This event is online: https://www.google.com/url?q=https://brown.zoom.us/j/91709235249andsa=Dandsource=calendarandust=1793023739589735& amp;usg=AOvVaw3LPMNnsk8MJoCy1ExTaXTMalk Title: Causal Vaccine Effects on Post-infection Outcomes in the Naturally Infected

Abstract:

Understanding vaccine effects on post-infection outcomes is critical for evaluating the full value proposition of a vaccine. However, defining appropriate causal effects on such outcomes can be challenging. We propose causal estimands for post-infection outcomes in the

Naturally Infected

subpopulation consisting of individuals who would be infected in absence of vaccine. We discuss partial identification using bounds and point identification and estimation using semi-parametric efficient one-step estimators with robustness properties under inconsistent nuisance parameter estimation. We further show under what conditions the same identification functional can be interpreted as targeting an effect among individuals exposed to a sufficiently infectious dose of the pathogen, thereby avoiding direct reliance on cross-world parameters and fundamentally untestable causal assumptions. We illustrate the method using an analysis of a rotavirus vaccine trial and simulation studies aimed to guide the design of

Shigella

vaccine trials.

This seminar will be held in-person and via Zoom. If you are unable to attend the seminar and would like the recording, please email Lauren Spencer (

lauren_spencer@brown.edu

lauren_spencer@brown.edu).

*Lunch will be provided on a first-come basis.

This event is online: https://www.google.com/url?q=https://brown.zoom.us/j/91709235249andsa=Dandsource=calendarandust=179 3023739589735andusg=AOvVaw3LPMNnsk8MJoCy1ExTaXTM