|
Activity Number:
|
32
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 2, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
| Abstract - #305214 |
|
Title:
|
A Power Comparison of Generalized Additive Models and the Spatial Scan Statistic Under Simple Alternative Hypotheses
|
|
Author(s):
|
Robin L. Young*+ and Janice Weinberg and Verónica Vieira and Thomas F. Webster
|
|
Companies:
|
Boston University School of Public Health and Boston University School of Public Health and Boston University School of Public Health and Boston University School of Public Health
|
|
Address:
|
, Boston, MA, ,
|
|
Keywords:
|
Generalized Additive Models ; Spatial Scan Statistic ; Power
|
|
Abstract:
|
The Generalized Additive Model (GAM) applied by Webster is a method to detect spatial variation in disease risk. The power of the GAM method has yet to be evaluated under simple scenarios where less advanced tests are appropriate. In this study, GAMs and Kulldorff's spatial scan statistic are applied to synthetic data under two simple scenarios and various alternative hypotheses. In the first scenario there exists a circular cluster within the study region; a chi-square test is appropriate. In the second scenario there is a negative linear association between the distance from the center of the region and the risk of disease; a simple logistic regression is appropriate. The powers of the GAM method and scan statistic are compared to each other, to the simpler chi-square test/logistic regression, and to the true theoretical power of the chi-square test/logistic regression.
|
- 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 2009 program |
