Time-series clustering via quasi U-statistics

Autor(es)

Valk, Marcio ^[1] ; Pinheiro, Aluisio ^[2]

Afiliação do(s) autor(es)

^[1] Univ Fed Rio Grande do Sul, BR-90046900 Porto Alegre, RS - Brazil

^[2] Univ Estadual Campinas, Dept Estat, Inst Matemat Estat & Comp Cient, BR-13083970 Campinas, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: JOURNAL OF TIME SERIES ANALYSIS; v. 33, n. 4, p. 608-619, JUL 2012.
• Citações Web of Science: 2

Resumo

The problem of time-series discrimination and classification is discussed. We propose a novel clustering algorithm based on a class of quasi U-statistics and subgroup decomposition tests. The decomposition may be applied to any concave time-series distance. The resulting test statistics are proven to be asymptotically normal for either i.i.d. or non-identically distributed groups of time-series under mild conditions. We illustrate its empirical performance on a simulation study and a real data analysis. The simulation setup includes stationary vs. stationary and stationary vs. non-stationary cases. The performance of the proposed method is favourably compared with some of the most common clustering measures available. (AU)

• Processo FAPESP: 09/14176-8 - Quase U-estatísticas, ondaletas e decomposabilidade: teoria assintótica e aplicações
• Beneficiário: Aluísio de Souza Pinheiro
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 08/51097-6 - Séries temporais, análise de dependência e aplicações
• Beneficiário: Pedro Alberto Morettin
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 07/02767-6 - O uso de quase $U$-estatísticas para séries temporais uni e multivariadas
• Beneficiário: Marcio Valk
• Modalidade de apoio: Bolsas no Brasil - Doutorado