|
Activity Number:
|
134
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 4, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #302141 |
|
Title:
|
A Transformation Binormal Model To Estimate the ROC Curve of a Continuous Biomarker
|
|
Author(s):
|
Danping Liu*+ and Andrew Zhou+
|
|
Companies:
|
University of Washington and University of Washington
|
|
Address:
|
F-600 Health Sciences Building, Seattle, WA, 98195-7232, , Seattle, WA, 98195,
|
|
Keywords:
|
ROC curve ; Binormal model ; Local polynomial ; Transformation model
|
|
Abstract:
|
Binormal models are widely used to estimate the ROC curve of a continuous biomarker, assuming the marker values for cases and controls both follow normal distributions with different location and scale parameters. We relax this assumption and set up a transformation binormal model (i.e., the normality of the marker values is achieved by an unknown monotone transformation). A local polynomial framework is adopted to estimate the transformation function. The individual covariates could be adjusted by considering some profile kernel estimating equations. Simulation studies are conducted to examine the performance of our estimate. The proposed method is applied to a real data set arising from the Alzheimer's disease research.
|
- 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 2008 program |
