|
Activity Number:
|
407
|
|
Type:
|
Roundtables
|
|
Date/Time:
|
Wednesday, August 6, 2008 : 12:30 PM to 1:50 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #301902 |
|
Title:
|
Bayesian Methods in the Evaluation of Modalities for Diagnosis and Prediction
|
|
Author(s):
|
Constantine Gatsonis*+
|
|
Companies:
|
Brown University
|
|
Address:
|
Center for Statistical Sciences, Providence, RI, 02912,
|
|
Keywords:
|
diagnosis ; prediction ; biomarkers ; ROC analysis ; sensitivity ; specificity
|
|
Abstract:
|
The Bayesian literature on the design and analysis of studies of diagnostic tests and biomarkers has had considerable growth in recent years. The majority of published work proposed parametric and nonparametric methods for studies assessing the sensitivity and specificity and/or the ROC curve of tests. Relatively less attention has been paid to the assessment of the predictive value of tests and questions of study design. In this roundtable, we will discuss current developments in this area of Bayesian methods and examine the experience from applying such methods in practice.
|
