Register here: https://ucdenverdata.formstack.com/forms/accords_2023_24_rabideau

Learning Objectives:

• Gain a basic understanding of cluster randomized trials and the key statistical complexities in their design and analysis.
• Learn how to conduct randomization tests and calculate randomization-based confidence intervals for CRTs.
• Reinforce concepts by working through a real data example together.

In a cluster randomized trial (CRT), groups of people are randomly assigned to different interventions. CRTs are useful when interventions are more naturally or feasibly applied at the cluster level or when we wish to quantify population-level effects. Common statistical methods for CRTs rely on distributional assumptions or a large number of clusters to provide valid p-values and confidence intervals. Randomization-based inference is an alternative approach that is distribution-free and does not require a large number of clusters to be valid. In this seminar, I will provide an overview of randomization-based inference for CRTs, demonstrate how to calculate randomization-based p-values and confidence intervals, and discuss some important practical considerations to keep in mind when conducting a randomization-based analysis.

About Dr. Rabideau:

Dustin Rabideau, PhD is the Associate Director of Biostatistics and Strategic Initiatives for Massachusetts General Hospital (MGH) Biostatistics, a faculty biostatistician MGH Biostatistics, and an Assistant Professor of Medicine at Harvard Medical School. He serves as Co-Investigator and Senior Biostatistician on local, national, and international research projects in psychiatry, cancer, and infectious diseases. Rabideau also leads two active areas of biostatistical research: robust analysis methods for cluster randomized trials and innovative methods to account for participant dropout in clinical trials.