Developing Bayesian Methods for Noninferiority Trial in Comparative Effectiveness Research [Methods Study], United States, 2015-2020 (ICPSR 39611)
Version Date: Jan 8, 2026 View help for published
Principal Investigator(s): View help for Principal Investigator(s)
Samiran Ghosh, Wayne State University
https://doi.org/10.3886/ICPSR39611.v1
Version V1
Summary View help for Summary
Researchers usually design studies to find out if a new treatment works better than no treatment or better than a treatment that is currently used. But sometimes researchers may want to know that a new treatment is not worse than one that's in use. These studies are called non-inferiority, or NI, studies. Researchers conduct NI studies when a new treatment has other benefits such as fewer side effects, even though it may not work better than the one in use. NI studies can provide useful information, but they are hard to design and conduct.
In this study, the research team tested different statistical methods for NI studies that compare treatments.
To access the methods and software, please visit the following Github repositories:
Citation View help for Citation
Export Citation:
Funding View help for Funding
Subject Terms View help for Subject Terms
Geographic Coverage View help for Geographic Coverage
Distributor(s) View help for Distributor(s)
Study Purpose View help for Study Purpose
To develop, evaluate, and apply novel adaptive bayesian statistical techniques to NI-based RCTs for CER. The specific aims are (1) conduct a prior elicitation based on multiple sources, including historical trials and patient and clinician opinions about treatments; (2) perform a meta-analysis that combined several priors into a super-prior; and (3) develop bayesian methods for the 2-arm and 3-arm NI trials
Study Design View help for Study Design
The research team proposed two ways of constructing a non-inferiority margin defined on the RR using a frequentist approach. Using the approach that resulted in greater power, the team developed a frequentist method, a fully Bayesian method, and two Bayesian approximation methods for hypothesis testing using RRs and ORs. The fully Bayesian method is more precise but computationally more demanding compared with the approximation methods.
Then the research team conducted simulation studies to evaluate the performance of the frequentist and Bayesian methods. Finally, the team tested the methods using a published data set from a study comparing the efficacy and safety of antibiotics for the treatment of complicated skin and skin structure infections with those of the standard therapy.
Data Source View help for Data Source
Simulated data; A published data set from a 2-arm study comparing antibiotics for complicated skin and skin structure infections
Notes
The public-use data files in this collection are available for access by the general public. Access does not require affiliation with an ICPSR member institution.
ICPSR usually offers files in multiple formats for researchers to be able to access data and documentation in formats that work well within their needs. If you have questions about the accessibility of materials distributed by ICPSR or require further assistance, please visit ICPSR’s Accessibility Center.