Online Program Home
  My Program

Abstract Details

Activity Number: 279 - Nonparametric Tests and Estimations for Clustered Data: It Is Essential for Non-Normal Data
Type: Topic Contributed
Date/Time: Tuesday, August 1, 2017 : 8:30 AM to 10:20 AM
Sponsor: International Chinese Statistical Association
Abstract #323119 View Presentation
Title: Pearson's Chi-Square Test and Rank Correlation Inferences for Clustered Data
Author(s): Joanna Shih* and Michael Fay
Companies: National Cancer Institute and National Institute of Allergy and Infectious Diseases
Keywords: Within-cluster resampling ; U-statistics ; Chi-square test ; Rank correlation

Pearson's chi-square test has been widely used in testing for association between two categorical responses. Spearman rank correlation and Kendall's tau are often used for measuring and testing association between two continuous or ordered categorical responses. However, the established statistical properties of these tests are only valid when each pair of responses are independent, where each sampling unit has only one pair of responses. When each sampling unit consists of a cluster of paired responses, the assumption of independent pairs is violated. In this article, we apply the within-cluster resampling technique to U-statistics to form new tests and rank-based correlation estimators for possibly tied clustered data. We develop large sample properties of the new proposed tests and estimators and evaluate their performance by simulations. The proposed methods are applied to a data set collected from a PET/CT imaging study for illustration.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

Copyright © American Statistical Association