Original link http://yamlb.wordpress.com/2006/06/19/the-us-fda-is-becoming-progressively-more-bayesian/
Date 2006-06-19
Status publish

The US Food and Drug Administration extensively uses statistical science, for instance for testing new drugs.... They mainly uses classical hypothesis testing and other frequencists procedure, but it seems that the bayesian methodology is becoming more popular. They recently published a Draft Guidance on Bayesian statistics. FDA is a leading authority as regards applied statitics.

This draft contains a lot of interesting remarks, showing the FDA point of vue:

Bayesian statistics is a statistical theory and approach to data analysis that provides a coherent method for learning from evidence as it accumulates.
Bayesian methods may be controversial when the prior information is based mainly on personal opinion (often derived by elicitation methods). The methods are often not controversial when the prior information is based on empirical evidence such as prior clinical trials.
The Bayesian approach, when correctly employed, may be less burdensome than a frequentist approach
The Bayesian methodology may reduce the sample size FDA needs to reach a regulatory decision.
With appropriate planning, the Bayesian approach can also offer the flexibility of midcourse changes to a trial.
A change in the prior information or the model at a later stage of the trial may imperil the scientific validity of the trial results.
The use of Bayesian hierarchical models enables us to combine information from different sources that may be exchangeable on some levels but not on others
Since the software used in Bayesian analysis is relatively new, FDA will often verify results using alternate software.
the frequentist approach makes extensive use of the likelihood function, it does not always strictly adhere to the likelihood principle.
Another way of saying this is that Bayesian inferences are based on the “parameter space”, while frequentist inferences are based on the “sample space”
In traditional frequentist clinical trial design, the sample size is determined in advance. Instead of specifying a particular sample size, the Bayesian approach (and some modern frequentist methods) may specify a particular criterion to stop the trial.
FDA believes the Bayesian approach is well suited for surveillance purposes.

They also provide some recommandation for designing a good bayesian data analysis procedure.