|
Activity Number:
|
176
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, August 4, 2008 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #301987 |
|
Title:
|
Evaluating the Accuracy of a Diagnostic Test When the Diagnostic Test Is Subject to Measurement Error Using an Internal Reliability Sample, with Applications to Alzheimer's Disease
|
|
Author(s):
|
Sharon X. Xie*+ and Christopher M. Clark
|
|
Companies:
|
University of Pennsylvania and University of Pennsylvania
|
|
Address:
|
423 Guardian Drive, Philadelphia, PA, 19104,
|
|
Keywords:
|
Sensitivity ; Specificity ; ROC curve ; Measurement error ; Alzheimer's disease
|
|
Abstract:
|
Cerebrospinal fluid (CSF) tau is useful in detecting Alzheimer's disease (AD). It is often assumed to measure the true biological quantity without error when its sensitivity and specificity are calculated. However, in practice this assumption almost never holds. When an internal reliability sample is available for CSF tau, we have shown that averaging replicates and ignoring measurement error can sometimes lead to serious biases of sensitivity and specificity estimates. We present a bias-correction approach to remove the biases of sensitivity and specificity estimates introduced by measurement error based on an internal reliability sample. Asymptotic distributions were obtained for the proposed estimators. Extensive simulations were conducted to evaluate the proposed approach. All methods are illustrated using the University of Pennsylvania AD biomarker study.
|
