Bayesian statistics is an approach for learning from evidence as it accumulates.
In clinical trials, frequentist statistical methods may use information from previous studies only at the design stage as in data analysis stage, this information is treated as complementary and not part of the formal analysis.
In contrast, the Bayesian approach uses Bayes’ Theorem to formally combine prior information with current information on a quantity of interest treating prior information and ongoing trial results as a continual data stream, in which inferences are being updated each time new data become available.
In the context of medical devices, addition of prior information in a Bayesian analysis increases precision and enables regulatory decision-making, while in some cases, use of prior information may decrease the required sample size .
A Bayesian approach
✔ offers flexibility in the design and analysis of adaptive trials
✔ may be used to obtain an exact analysis when the corresponding frequentist analysis is only approximate or is difficult to implement
✔ allows for great flexibility in dealing with missing data
✔ may be advantageous in managing #multiplicity adjustments
Check our presentation to read more on the challenges involved with Bayesian statistics!
