Clustering multivariate time series using energy distance
- 27 March 2023
- journal article
- research article
- Published by Wiley in Journal of Time Series Analysis
- Vol. 44 (5-6) , 487-504
Abstract
A novel methodology is proposed for clustering multivariate time series data using energy distance defined in Székely and Rizzo (2013). Specifically, a dissimilarity matrix is formed using the energy distance statistic to measure the separation between the finite‐dimensional distributions for the component time series. Once the pairwise dissimilarity matrix is calculated, a hierarchical clustering method is then applied to obtain the dendrogram. This procedure is completely nonparametric as the dissimilarities between stationary distributions are directly calculated without making any model assumptions. In order to justify this procedure, asymptotic properties of the energy distance estimates are derived for general stationary and ergodic time series. The method is illustrated in a simulation study for various component time series that are either linear or nonlinear. Finally, the methodology is applied to two examples; one involves the GDP of selected countries and the other is the population size of various states in the U.S.A. in the years 1900–1999.Keywords
All Related Versions
Funding Information
- National Science Foundation (DMS‐201537)
This publication has 29 references indexed in Scilit:
- A review on time series data miningEngineering Applications of Artificial Intelligence, 2011
- Clustering of biological time series by cepstral coefficients based distancesPattern Recognition, 2008
- Measuring and testing dependence by correlation of distancesThe Annals of Statistics, 2007
- A periodogram-based metric for time series classificationComputational Statistics & Data Analysis, 2006
- Clustering of time series data—a surveyPattern Recognition, 2005
- Discrimination and Clustering for Multivariate Time SeriesJournal of the American Statistical Association, 1998
- A DISTANCE MEASURE FOR CLASSIFYING ARIMA MODELSJournal of Time Series Analysis, 1990
- Comparing partitionsJournal of Classification, 1985
- 1 Discriminant analysis for time series1982
- Objective Criteria for the Evaluation of Clustering MethodsJournal of the American Statistical Association, 1971