Biostatistics Seminar Series

Donglin Zeng - Sequential Multiple Assignment Randomization Trials with Enrichment Design

Thursday 9/22 3:30PM - 4:30PM
Public Health Auditorium (G23)

This week's weekly Biostatistics Seminar will feature Dr. Donglin Zeng, professor at UNC Gillings School of Global Public Health, and the co-director of the Carolina Survey Research Laboratory

ABSTRACT

Sequential Multiple Assignment Randomization Trials with Enrichment Design

Sequential multiple assignment randomization trial (SMART) is a powerful design to study Dynamic Treatment Regimes (DTRs) and allows causal comparisons of DTRs. To handle practical challenges of SMART, we propose a SMART with Enrichment design (SMARTer), which performs stage-wise enrichment for SMART.  Specifically, at each subsequent stage of a SMART, we enrich the study sample with new patients who have received previous stages' treatments in a naturalistic fashion without randomization, and only randomize them among the current stage treatment options. One extreme case of the  SMARTer is to synthesize separate independent single-stage randomized trials  with patients who have received previous stage treatments. We show data from SMARTer  allows for unbiased estimation of DTRs as  SMART does under certain assumptions. Furthermore,  we show analytically that the efficiency gain of the new design over SMART can be significant especially when the dropout rate is high.  Lastly, extensive simulation studies are performed to demonstrate performance of SMARTer design, and  sample size estimation in a scenario informed by real data from a SMART study is presented.

*This is joint work with Drs. Ying Liu and Yuanjia Wang

 

 

Last Updated On Tuesday, August 30, 2016 by Valenti, Renee Nerozzi
Created On Thursday, July 14, 2016