Skip to main content
SpringerLink
Log in

Clustering of time series using quantile autocovariances

  • Regular Article
  • Published:
Advances in Data Analysis and Classification Aims and scope Submit manuscript

Abstract

Time series clustering is an active research topic with applications in many fields. Unlike conventional clustering on multivariate data, time series often change over time so that the similarity concept between objects must take into account the dynamic of the series. In this paper, a distance measure aimed to compare quantile autocovariance functions is proposed to perform clustering of time series. Quantile autocovariances provide information about the serial dependence structure at different pairs of quantile levels, require no moment condition and allow to identify dependence features that covariance-based methods are unable to detect. Results from an extensive simulation study show that the proposed metric outperforms or is highly competitive with a range of dissimilarities reported in the literature, particularly exhibiting high capability to cluster time series generated from a broad range of dependence models. Estimation of the optimal number of clusters is also addressed. For illustrative purposes, our methodology is applied to a real dataset involving financial time series.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Notes

  1. http://www.bancaditalia.it/banca_centrale/cambi/rif;internal&action=_set-language.action?LANGUAGE=en.

References

  • Advances in Data Analysis and Classification (2011) Special issue on “Time series clustering”, vol 5(4). Springer, New York

  • Caiado J, Crato N, Peña D (2006) A periodogram-based metric for time series classification. Comput Stat Data Anal 50(10):2668–2684

    Article  MathSciNet  MATH  Google Scholar 

  • Caliński T, Harabasz J (1974) A dendrite method for cluster analysis. Commun Stat Simul Comput 3(1):1–27

    Article  MathSciNet  MATH  Google Scholar 

  • Chen C, Wei Y (2005) Computational issues for quantile regression. Sankhyā Indian J Stat 67:399–417

  • Corduas M, Piccolo D (2008) Time series clustering and classification by the autoregressive metric. Comput Stat Data Anal 52(4):1860–1872

    Article  MathSciNet  MATH  Google Scholar 

  • Davis RA, Mikosch T (1998) The sample autocorrelations of heavy-tailed processes with applications to arch. Ann Stat 26(5):2049–2080

    Article  MathSciNet  MATH  Google Scholar 

  • Davis RA, Mikosch T (2009) The extremogram: a correlogram for extreme events. Bernoulli 15(4):977–1009

    Article  MathSciNet  MATH  Google Scholar 

  • De Luca G, Zuccolotto P (2011) A tail dependence-based dissimilarity measure for financial time series clustering. Adv Data Anal Classif 5(4):323–340

    Article  MathSciNet  Google Scholar 

  • Dette H, Hallin M, Kley T, Volgushev S (2014) Of copulas, quantiles, ranks and spectra: An \(l_1\)-approach to spectral analysis. Unpublished manuscript, arXiv:1111.7205v2

  • Dudoit S, Fridlyand J (2002) A prediction-based resampling method for estimating the number of clusters in a dataset. Genome Biol 3(7):research0036.1–research0036.21

    Article  Google Scholar 

  • D’Urso P, Maharaj EA (2009) Autocorrelation-based fuzzy clustering of time series. Fuzzy Sets Syst 160(24):3565–3589

    Article  MathSciNet  Google Scholar 

  • D’Urso P, Cappelli C, Lallo DD, Massari R (2013) Clustering of financial time series. Physica A 392(9):2114–2129

    Article  MathSciNet  Google Scholar 

  • Frühwirth-Schnatter S (2011) Adv Data Anal Classif 5(4):251–280

  • Frühwirth-Schnatter S, Kaufmann S (2008) Model-based clustering of multiple time series. J Business Econ Stat 26(1):78–89

    Article  MathSciNet  Google Scholar 

  • Tc Fu (2011) A review on time series data mining. Eng Appl Artif Intell 24(1):164–181

    Article  Google Scholar 

  • Gavrilov M, Anguelov D, Indyk P, Motwani R (2000) Mining the stock market (extended abstract): which measure is best? In: Proceedings of the sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, New York, KDD’00, pp 487–496

  • Hagemann A (2013) Robust spectral analysis. Unpublished manuscript, arXiv:1111.1965v1

  • Hartigan JA (1975) Clustering algorithms, 99th edn. Wiley, New York

    MATH  Google Scholar 

  • Hong Y (2000) Generalized spectral tests for serial dependence. J R Stat Soc Ser B Stat Methodol 62(3):557–574

    Article  MathSciNet  MATH  Google Scholar 

  • Hubert L, Arabie P (1985) Comparing partitions. J Classif 2(1):193–218

    Article  MATH  Google Scholar 

  • Hyndman RJ, Fan Y (1996) Sample quantiles in statistical packages. Am Stat 50(4):361–365

    Google Scholar 

  • Kao SC, Ganguly AR, Steinhaeuser K (2009) Motivating complex dependence structures in data mining: A case study with anomaly detection in climate. In: Saygin Y, Yu JX, Kargupta H, Ranka S, Yu PS, Wu X (eds) 2013 IEEE 13th International Conference on Data Mining Workshops, IEEE Computer Society, Los Alamitos, pp 223–230

  • Kaufman L, Rousseeuw PJ (1990) Finding groups in data: an introduction to cluster analysis. Wiley, New York

    Book  Google Scholar 

  • Keogh E, Kasetty S (2003) On the need for time series data mining benchmarks: A survey and empirical demonstration. Data Min Knowl Discov 7(4):349–371

    Article  MathSciNet  Google Scholar 

  • Koenker R (2005) Quantile regression. Econometric Society Monographs, Cambridge

    Book  MATH  Google Scholar 

  • Koenker RW, D’Orey V (1987) Algorithm as 229: computing regression quantiles. J Royal Stat Soc Series C Appl Stat 36(3):383–393

    Google Scholar 

  • Krzanowski WJ, Lai YT (1988) A criterion for determining the number of groups in a data set using sum-of-squares clustering. Biometrics 44(1):23–34

    Article  MathSciNet  MATH  Google Scholar 

  • Lee J, Rao S (2012) The quantile spectral density and comparison based tests for nonlinear time series. Unpublished manuscript, Department of Statistics, Texas A&M University, College Station, arXiv:1112.2759v2

  • Li TH (2014) Quantile periodograms. J Am Stat Assoc 107(498):765–776

    Article  MathSciNet  MATH  Google Scholar 

  • Liao TW (2005) Clustering of time series data: a survey. Pattern Recognit 38(11):1857–1874

    Article  MATH  Google Scholar 

  • Linton O, Whang YJ (2007) The quantilogram: with an application to evaluating directional predictability. J Econom 141(1):250–282

    Article  MathSciNet  MATH  Google Scholar 

  • Maharaj EA (1996) A significance test for classifying ARMA models. J Stat Comput Simul 54(4):305–331

    Article  MathSciNet  MATH  Google Scholar 

  • Maharaj EA (2000) Clusters of time series. J Classifi 17(2):297–314

    Article  MathSciNet  MATH  Google Scholar 

  • Mikosch T, Stărică C (2000) Limit theory for the sample autocorrelations and extremes of a garch (1,1) process. Ann Stat 28(5):1427–1451

    Article  MathSciNet  MATH  Google Scholar 

  • Montero P, Vilar JA (2014a) TSclust: An \(\sf R\) package for time series clustering. J Stat Softw 62(1):1–43

  • Montero P, Vilar JA (2014b) TSclust: Time series clustering utilities. http://CRAN.R-project.org/package=TSclust, \(\sf R\) package version 1.2.1

  • Otranto E (2008) Clustering heteroskedastic time series by model-based procedures. Comput Stat Data Anal 52(10):4685–4698

    Article  MathSciNet  MATH  Google Scholar 

  • Pértega S, Vilar JA (2010) Comparing several parametric and nonparametric approaches to time series clustering: a simulation study. J Classif 27(3):333–362

    Article  MathSciNet  MATH  Google Scholar 

  • Piccolo D (1990) A distance measure for classifying arima models. J Time Series Anal 11(2):153–164

    Article  MATH  Google Scholar 

  • Ramoni M, Sebastiani P, Cohen P (2002) Bayesian clustering by dynamics. Mach Learn 47(1):91–121

    Article  MATH  Google Scholar 

  • \(\sf R\) Core Team (2014) \(\sf R\): A language and environment for statistical computing. \(\sf R\) Foundation for Statistical Computing, Vienna, Austria. http://www.R-project.org/

  • Skaug HJ, Tjøstheim D (1993) nonparametric test of serial independence based on the empirical distribution function. Biometrika 80(3):591–602

    Article  MathSciNet  MATH  Google Scholar 

  • Taylor S (2007) Modelling financial time series. Wiley, New York

    Book  MATH  Google Scholar 

  • Tibshirani R, Walther G, Hastie T (2001) Estimating the number of clusters in a data set via the gap statistic. J R Stat Soc Ser B Stat Methodol 63:411–423

    Article  MathSciNet  MATH  Google Scholar 

  • Vilar JA, Pértega S (2004) Discriminant and cluster analysis for gaussian stationary processes: local linear fitting approach. J Nonparametr Stat 16(3–4):443–462

    Article  MathSciNet  MATH  Google Scholar 

  • Vilar JA, Alonso AM, Vilar JM (2010) Non-linear time series clustering based on non-parametric forecast densities. Comput Stat Data Anal 54(11):2850–2865

    Article  MathSciNet  MATH  Google Scholar 

  • Wang X, Mueen A, Ding H, Trajcevski G, Scheuermann P, Keogh EJ (2013) Experimental comparison of representation methods and distance measures for time series data. Data Min Knowl Discov 26(2):275–309

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgments

The authors wish to thank the three anonymous reviewers and the Editors for their helpful comments and valuable suggestions, which have allowed us to improve the quality of this work. This research was supported by the Spanish grants MTM2011-22392 and MTM2014-52876-R from the Ministerio de Economía y Competitividad.

Author information

Authors and Affiliations

  1. Research Group on Modeling, Optimization and Statistical Inference (MODES), Department of Mathematics, Computer Science Faculty, University of A Coruña, 15071, A Coruña, Spain

    Borja Lafuente-Rego & José A. Vilar

Authors
  1. Borja Lafuente-Rego
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. José A. Vilar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Borja Lafuente-Rego.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lafuente-Rego, B., Vilar, J.A. Clustering of time series using quantile autocovariances. Adv Data Anal Classif 10, 391–415 (2016). https://doi.org/10.1007/s11634-015-0208-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11634-015-0208-8

Keywords

Mathematics Subject Classification

Search

Navigation