Activity Number:
|
518
- Estimand, Causal Inference, and Other Statistical Considerations in Clinical Trials
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 11, 2022 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Biopharmaceutical Section
|
Abstract #323038
|
|
Title:
|
Connecting P-Values and Posterior Probabilities Through Bayes Factor Bound: A Brief History and Its Application
|
Author(s):
|
Xiting Yang* and Greg Maislin and Dongfeng Qi
|
Companies:
|
FDA and Biomedical Statistical Consulting and Boston Scientific
|
Keywords:
|
p-value;
Bayes Factor Bound;
clinical trial
|
Abstract:
|
P-values have long been used in null hypothesis significance testing (NHST). However, often ignored in practice is that one needs the context (i.e. prior knowledge) to interpret the p-value properly. Since Bayesian posterior probability naturally incorporates prior knowledge, in this talk, we’ll show how Bayes Factor Bound (BFB) can be used to derive an upper bound of the posterior probability of H1 from p-value. We’ll include a brief history of BFB and show its application in a clinical trial setting.
|
Authors who are presenting talks have a * after their name.