Methods: Mind the Gap

Webinar Series

Analysis of Multiple-Period Group-Randomized Trials: Random Coefficients Model or Repeated Measures ANOVA?

August 11, 2023
Jonathan Moyer
Jonathan Moyer, Ph.D.

NIH Office of Disease Prevention

View the Webinar

About the Webinar

NIH Collaboratory Webinar Series

If you enjoyed this Methods: Mind the Gap webinar, check out the NIH Collaboratory's webinar series, Advances in the Design and Analysis of Pragmatic Clinical Trials, highlighting approaches to the design and analysis of pragmatic trials.

The series started on October 6, 2023 with a presentation by ODP Director Dr. David Murray titled “Hybrid Studies Should Not Sacrifice Rigorous Methods.” ODP staff member Dr. Jon Moyer also presented on “The Perils and Pitfalls of Complex Clustering in Pragmatic Trials.”

Multiple-period parallel group-randomized trials (GRTs) can represent time as continuous or categorical in analytic models. Previous work has recommended representing time as a continuous variable in multiple-period parallel GRTs because analytic models representing time as continuous maintained a nominal type I error rate when applied to data generated assuming time was either continuous or categorical. In contrast, analytic models representing time as categorical exhibited an inflated type I error rate when applied to data generated assuming time was continuous.

This webinar presents results of a simulation study comparing both approaches, updating the previous study by applying more sophisticated analytic models and assessing the impact of ignoring time by group variation in analytic models when such variation is present in the data generating mechanism. After providing background on multiple-period parallel GRTs including analytic models and covariance structures, Dr. Jonathan Moyer uses simulations to compare the type I error rates of analytic models representing time as continuous or categorical. 

About Jonathan Moyer

Dr. Jonathan Moyer is a statistician focusing on efforts to enhance the rigor and reproducibility of NIH-funded prevention research by promoting the use of the best available research methods. This includes expanding the resources available on NIH’s Research Methods Resources website, providing guidance on the Methods: Mind the Gap Webinar Series, and collaborating with NIH Institutes and Centers on projects that require group randomization or delivery of interventions to groups.

 

Last updated on