Activity Number:
|
8
- Statistics and the Reproducibility Crisis
|
Type:
|
Invited
|
Date/Time:
|
Sunday, July 30, 2017 : 2:00 PM to 3:50 PM
|
Sponsor:
|
The American Statistician
|
Abstract #322099
|
View Presentation
|
Title:
|
P-Values: Variability, Reproducibility and Lessons from Multiple Testing
|
Author(s):
|
Naomi Altman*
|
Companies:
|
Penn State University
|
Keywords:
|
sampling distribution ;
rejection ratio ;
rejection odds ;
pi_0 ;
false discovery
|
Abstract:
|
P-values are frequently misused and misunderstood as evidence. The sample to sample variability of p-values and the effects of multiple testing (explicit or implicit) are seldom appreciated by scientists using p-values to summarize their studies. In this talk I discuss some of the important features of the sampling distribution of p-values under continuous and discrete testing. I will also share some ideas of how the concept of false discovery rate can assist in calibrating p-values for better interpretability.
|
Authors who are presenting talks have a * after their name.