Premium
Equidirection: A Measure of Similarity Among Time Series
Author(s) -
Yassouridis A.,
Hansert E.
Publication year - 1986
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.4710280616
Subject(s) - series (stratigraphy) , measure (data warehouse) , mathematics , similarity (geometry) , variation (astronomy) , similarity measure , identification (biology) , time series , statistics , computer science , data mining , artificial intelligence , paleontology , physics , botany , astrophysics , image (mathematics) , biology
In the present paper we investigate the concept of equidirection, i.e. similarity in the direction of variation, or parallelism in the broader sense, among m (m ≧ 2) times series, especially under the assumption that the time series are realizations of processes with independent increments. However, the processes need not be stationary. Furthermore, the probabilities for the direction of variation may be unstable, in which case only upper and lower bounds are known. A measure based on the concept of equidirection was developed that enables identification of clusters of similar time series and analysis of relationships among variables.