|
Activity Number:
|
437
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #305683 |
|
Title:
|
Confidence Interval for the Odds Ratio Using Double Sampling
|
|
Author(s):
|
Denka Markova*+ and Dean Young
|
|
Companies:
|
Baylor University and Baylor University
|
|
Address:
|
One Bear Place, Waco, TX, 76798,
|
|
Keywords:
|
|
|
Abstract:
|
The double sampling plan has become an important part of the epidemiological designs. The plan includes two stages. First, the individual is classified by disease and exposure levels using a fallible test, and second, the individual is classified using a "gold standard" test. The parameter of interest in the study is the odds ratio as an association between disease level and exposure level. In our study we examine the confidence interval for the odds ratio under the assumption of non-differential misclassification. We compare the coverage of the Wald and Score confidence intervals based on different specificity and sensitivity values. We derive results for both case-control and cohort studies.
|
