A smoothed bootstrap test for independence based on mutual information

Edmond H.C. WU, Philip L.H. YU, Wai Keung LI

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

A test for independence of multivariate time series based on the mutual information measure is proposed. First of all, a test for independence between two variables based on i.i.d. (time-independent) data is constructed and is then extended to incorporate higher dimensions and strictly stationary time series data. The smoothed bootstrap method is used to estimate the null distribution of mutual information. The experimental results reveal that the proposed smoothed bootstrap test performs better than the existing tests and can achieve high powers even for moderate dependence structures. Finally, the proposed test is applied to assess the actual independence of components obtained from independent component analysis (ICA). Copyright © 2008 Elsevier B.V. All rights reserved.
Original languageEnglish
Pages (from-to)2524-2536
JournalComputational Statistics and Data Analysis
Volume53
Issue number7
DOIs
Publication statusPublished - May 2009

Fingerprint

Smoothed Bootstrap
Bootstrap Test
Mutual Information
Time series
Independent component analysis
Stationary Time Series
Multivariate Time Series
Information Measure
Bootstrap Method
Dependence Structure
Null Distribution
Independent Component Analysis
Time Series Data
High Power
Higher Dimensions
Strictly
Independence
Experimental Results
Estimate

Citation

Wu, E. H. C., Yu, P. L. H., & Li, W. K. (2009). A smoothed bootstrap test for independence based on mutual information. Computational Statistics and Data Analysis, 53(7), 2524-2536. doi: 10.1016/j.csda.2008.11.032