|
Activity Number:
|
76
- Contributed Poster Presentations: Section on Statistics in Epidemiology
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 3, 2020 : 10:00 AM to 2:00 PM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
|
Abstract #313581
|
|
|
Title:
|
Power and Sample Size for the Test Negative Design
|
|
Author(s):
|
Yanan Huo* and Natalie Dean
|
|
Companies:
|
and University of Florida
|
|
Keywords:
|
Test negative design;
vacccines;
sample size;
score test;
counting process
|
|
Abstract:
|
The test-negative design (TND) is a recent epidemiological study design used to evaluate vaccine effectiveness. The TND enrolls individuals receiving testing for a target disease as part of routine care. Vaccine effectiveness is estimated from the odds ratio of testing positive for vaccinated versus unvaccinated patients without requiring rare disease assumption. No guidance is available on sample size and planning for TND studies. The TND is related to case-control studies while sharing similar uncertainties with cross-sectional studies. The Wald test performs poorly in both case-control and TND studies when vaccine effectiveness is high. The variance estimator is unstable when the expected test positive vaccinated cell count is low. Continuity corrections help to stabilize the variance but induce bias. We recommend using a score-based approach to design and analyze TND studies. We distinguish the TND and case-control studies by quantifying the additional variability. We examine the likelihood of the TND using stochastic processes to model the underlying data generating mechanism. Repeated testing is allowed. We develop the TND sample size counting for the additional variability.
|
Authors who are presenting talks have a * after their name.
