Double Negative Control Inference in Test-Negative Design Studies of Vaccine Effectiveness
Xu Shi, PhD
Assistant Professor, Department of Biostatistics
University of Michigan
WHEN: Wednesday, February 14, 2024, from 3:30 to 4:30 p.m.
WHERE: hybrid | 2001 McGill College Avenue, room 1140;
NOTE: Dr. Shi will be presenting from Michigan
Abstract
The test-negative design (TND) has become a standard approach to evaluate vaccine effectiveness. Despite TND's potential to reduce unobserved differences in healthcare-seeking behavior (HSB) between vaccinated and unvaccinated subjects, it remains subject to various potential biases. First, residual confounding bias may remain due to unobserved HSB, occupation as a healthcare worker, or previous infection history. Second, because selection into the TND sample is a common consequence of infection and HSB, collider stratification bias may exist when conditioning the analysis on testing, which further induces confounding by latent HSB. Third, generalizability of the results to the general population is not guaranteed. In this talk, we present a novel approach to identify and estimate vaccine effectiveness in the general population by carefully leveraging a pair of negative control exposure and outcome variables to account for potential hidden bias in TND studies. We illustrate our proposed method with extensive simulation and an application to COVID-19 vaccine effectiveness using data from the University of Michigan Health System.
Speaker bio
Xu Shi is an Assistant Professor in the Department of Biostatistics at the University of Michigan. She is interested in developing statistical methods for electronic health records and claims data, focusing on causal inference, data harmonization across healthcare systems and comparative effectiveness and safety research.