|
Activity Number:
|
260
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #304086 |
|
Title:
|
Nonparametric Estimation of the Disease Attributable Fraction
|
|
Author(s):
|
Wei Wang*+
|
|
Companies:
|
University of Pennsylvania
|
|
Address:
|
400 Huntsman Hall, Philadelphia, PA, 19104,
|
|
Keywords:
|
disease attributable fraction ; monotone regression
|
|
Abstract:
|
The disease attributable fraction for a given exposure is the proportion of the disease cases that can be attributed to an exposure. Under certain assumptions, estimation of the disease attributable fraction involves estimating the probability of having the disease given exposure level and is of particular importance to estimate the probability of disease given zero exposure. It is often natural to impose the assumption that the probability of having the disease is a monotone increasing function of the exposure. We develop a method to estimate the disease attributable fraction under the monotonicity restriction. We compare our method with other traditional methods and show that our approach achieves smaller MSE.
|
