|
Activity Number:
|
55
- Complex Functional and Non-Euclidean Data Analysis
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Sunday, August 7, 2022 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
|
Abstract #322167
|
|
|
Title:
|
Testing Marginal Homogeneity for Functional Data
|
|
Author(s):
|
Jane-Ling Wang* and Changbo Zhu
|
|
Companies:
|
University of California, Davis and University of California, Davis
|
|
Keywords:
|
Energy distance;
Longitudinal data;
Measurement errors;
Phase transition;
Two-sample test
|
|
Abstract:
|
Testing the homogeneity between two samples of functional data is an important task. We propose a two sample statistic that targets point-wise distributions and works well with both intensely and sparsely measured functional data. The proposed testing procedure is formulated upon Energy distance, where the critical values are obtained via permutations. Convergence rate of the test statistic to its population version is derived with a phase transition in the convergence rate that is determined by the sampling frequency. The aptness of our method is demonstrated on both synthetic and real data sets.
|
Authors who are presenting talks have a * after their name.
