|
Activity Number:
|
49
|
|
Type:
|
Invited
|
|
Date/Time:
|
Sunday, August 6, 2006 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
The American Statistician
|
| Abstract - #305087 |
|
Title:
|
"Bad" Statistical Methods: What Are the Costs?
|
|
Author(s):
|
David Freedman*+ and S. Stanley Young*+ and Mary Foulkes*+ and Juliet Shaffer*+
|
|
Companies:
|
University of California, Berkeley and National Institute of Statistical Sciences and U.S. Food and Drug Administration and University of California, Berkeley
|
|
Address:
|
, , , , , , CBER, , , , , ,
|
|
Keywords:
|
research methods ; loss ; risk ; publication ; procedures
|
|
Abstract:
|
Statistics are used increasingly in cases where costs and benefits are important, including litigation, credit scoring, fraud and terrorism detection, scientific technology transfer, and scientific policymaking. We have all seen examples of statistical methods, procedures, and protocols that are suspect at best---and completely inappropriate at worst. Yet, in many cases, such methods continue to be used and enjoy popularity in their respective scientific disciplines. If 'bad' methods are used, are they really that 'bad'? What are the real costs of using 'bad' statistical methods?
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2006 program |
