Activity Number:
|
409
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 15, 2002 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistical Computing*
|
Abstract - #300782 |
Title:
|
On Determination of Sample Size for the Positive Kappa Coefficient
|
Author(s):
|
Tze-San Lee*+
|
Affiliation(s):
|
National Center for HIV, STD, and TB
|
Address:
|
Building 11, Corporate Square, Atlanta, Georgia, 30333, USA
|
Keywords:
|
diagnostic test ; kappa coefficient ; sample size requirement ; tuberculosis
|
Abstract:
|
The kappa coefficient is used to express the degree of the interrater's agreement. In the context of epidemiology, the kappa coefficient is similarly applied to indicate the degree of the agreement between two diagnostic tests for detecting a certain infectious disease when neither of the two tests can be regarded as a gold standard. Sample-size determinations are discussed if the kappa coefficient is desired to be no less than a certain proportion. The formula for sample size depends on three parameters, namely, the copositive proportion of, and the positive proportions of, the two diagnostic tests. An application to two diagnostic tests for detecting tuberculosis is given for an illustration.
|
- 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 2002 program |