A power calculation is only as good as its weakest assumption. As an FDA reviewer, when I saw a treatment difference or a completion rate with no source, I looked harder at everything else. Issue 3: where sample size assumptions go wrong. www.thesignificantdifference.com/issue3

When a submission didn't match its own analysis plan, I always asked: When was this decision made, and what did the data look like at that point? That question ended more conversations than any other. Issue 2: www.thesignificantdifference.com/p/your-sap-i...

What FDA Reviewers Look For in a Statistical Analysis Plan (SAP)

Former FDA Master Statistical Reviewer on what makes a statistical analysis plan credible: estimands, multiplicity, deviations, and early FDA review.

thesignificantdifference.com

The fastest reviews I did had one thing in common, and it wasn't the p-value. It was whether the protocol, the SAP and the reported results told one story. More in Issue 1 of The Significant Difference ↓

The first thing an FDA statistician looks for (it's not the p-value)

What FDA's reviewers see — and what sponsors need to know

thesignificantdifference.com

I spent 24 years at FDA reviewing the statistics in NDA and BLA submissions. Now I write The Significant Difference: what FDA's reviewers see, and what sponsors need to know. Short, practical, from the reviewer's side of the table. www.thesignificantdifference.com