|
Activity Number:
|
510
- Recent Development in Semiparametric and Nonparametric Methods
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, July 31, 2019 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
International Chinese Statistical Association
|
|
Abstract #305261
|
|
|
Title:
|
Nonparametric Multivariate Tests for Association
|
|
Author(s):
|
Yan Xu* and Solomon W. Harrar
|
|
Companies:
|
and University of Kentucky
|
|
Keywords:
|
Nonparametric;
MCTP;
multivariate data
|
|
Abstract:
|
Testing existence of an association between a multivariate response and predictors is an important data analytic task. In this test, we present a nonparametric procedure that makes no specific distributional, regression function and covariance matrix assumptions. Our test is motivated by recent results in high-dimensional multivariate analysis. The test is constructed by deriving asymptotic joint distribution of suitable univariate statistics for testing association between each response and the predictors. Then multiple contrast testing procedure (MCTP) is applied to get a number of multivariate tests. The finite sample properties of the tests are demonstrated using simulation studies. Data from a smoking cessation trial will be used to illustrate the application of the tests.
|
Authors who are presenting talks have a * after their name.
