JSM 2015 Preliminary Program

Online Program Home
My Program

Abstract Details

Activity Number: 300
Type: Topic Contributed
Date/Time: Tuesday, August 11, 2015 : 8:30 AM to 10:20 AM
Sponsor: Biopharmaceutical Section
Abstract #315908 View Presentation
Title: Consequences of Misspecified Clusters in Group Randomized Trials
Author(s): Abigail Shoben* and Rebecca Andridge and David M. Murray
Companies: The Ohio State University and The Ohio State University and NIH
Keywords: cluster randomized trials ; correlated data ; clinical trials
Abstract:

Participants in group randomized trials (GRTs) or in individually randomized group treatment (IRGT) trials who share a group (or change agent) are expected to have positively correlated outcome measurements. Standard statistical methods can account for this correlation, assuming that group membership remains stable for the duration. We considered the case of individual participants switching groups during a group randomized or IRGT trial. Group switching may cause the assumption of independence between individuals who began the study in different groups to be violated. Our simulations show that the standard approach of modeling only the original group leads to inflated type I error rates in many realistic circumstances. The problem is exacerbated as the probability of switching groups increases, the magnitude of the intraclass correlation increases, and the number of participants per group increases. Modeling the group a participant belonged to for the longest period of time rather than only the original group for each participant resulted in generally lower type I error rates, but was not enough to keep the type I error rate at the nominal level in all circumstances.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2015 program





For program information, contact the JSM Registration Department or phone (888) 231-3473.

For Professional Development information, contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

2015 JSM Online Program Home