Online Program Home
My Program

Abstract Details

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 #304902
Title: Nonparametric Tests for Multivariate Growth Curve Data: Practical Procedures in Finite Samples
Author(s): Ting Zeng* and Solomon W. Harrar
Companies: University of Kentucky and University of Kentucky
Keywords: Ranks; Resampling; Repeated Measures; Ordinal data; Semi-parametric inference; Finite sample approximation

In this talk, nonparametric methods for multivariate growth curve data are presented. In the semi-parametric situation where mean-based inference is sought, parametric and nonparametric bootstraps are known to have satisfactory finite sample performance in the general factorial designs. In this regard, our aim is to provide a resampling-based tests for multivariate growth curve data that are useful in the situations where the data is not necessarily exchangeable under the null hypothesis of interest. In some studies, the outcome of interest may not be amenable for a mean-based inference. For example, in studies that target management of chronic disease, Quality of Life (QoL) outcomes measured in order-categorical scales are used. For these situations, we propose a resampling-based fully nonparametric procedures. Simulation studies are conducted to evaluate the finite sample performance of the proposed procedures under various practical scenarios. Data from a Pediatric Asthma Prevention Study and an optometry study will be used to illustrate the benefits of the nonparametric methods proposed.

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

Back to the full JSM 2019 program