|
Activity Number:
|
470
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 9, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #307555 |
|
Title:
|
Smoothing Spline Anova Model for Bivariate Bernoulli Outcome
|
|
Author(s):
|
Hyonho Chun*+
|
|
Companies:
|
University of Wisconsin-Madison
|
|
Address:
|
5639 Longford Terrace 104, Fitchburg, WI, 53711,
|
|
Keywords:
|
smoothing spline ANOVA ; log odds ratio ; logit
|
|
Abstract:
|
The parameters of a bivariate Bernoulli density with canonical parameterization have forms which have nice interpretations - one for logit function and the other for log odds ratio. Usually, log odds ratio is estimated as a constant, but here special attention is on estimating the log odds ratio as a smooth function of covariates. Not only logit function but also log odds ratio function will be estimated in a very flexible way by using smoothing spline ANOVA model. This will reveal interesting behavior of log odds ratio function. The large sample behavior of the estimator will be investigated. This formulation will be utilized for assessing familial aggregation of a disease.
|
- 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 2006 program |
