YSPH Biostatistics Seminar- “Time-Varying Treatment Effects and Redesign of Stepped-Wedge Cluster Randomized Trials”

Note: BIS 526 students are required to attend in person. Others are invited to attend in person but may also attend via zoom.

Speaker Rui Feng, Ph.D.

Title: “Time-Varying Treatment Effects and Redesign of Stepped-Wedge Cluster Randomized Trials”

Abstract

Stepped-wedge cluster randomized trials introduce interventions sequentially across clusters and commonly assume constant treatment effects over time. In practice, treatment effects often vary with time, and violations of this homogeneity assumption can lead to biased inference.

In this talk, I establish identifiability conditions for time-varying, piecewise treatment effects in two-arm and three-arm stepped-wedge trials and show how conventional designs yield biased treatment and time-effect estimates under misspecification. Simulations demonstrate inflated Type I error and bias in both main and interaction effects. I then illustrate the practical implications using the DROP-BENZO trial, showing that estimates under minimal homogeneity and limited time-adjustment assumptions are more plausible than those obtained under full homogeneity.