Clusters of effects curves in quantile regression models

Computational Statistics volume 34, pages551–569(2019)Cite this article

Abstract

In this paper, we propose a new method for finding similarity of effects based on quantile regression models. Clustering of effects curves (CEC) techniques are applied to quantile regression coefficients, which are one-to-one functions of the order of the quantile. We adopt the quantile regression coefficients modeling (QRCM) framework to describe the functional form of the coefficient functions by means of parametric models. The proposed method can be utilized to cluster the effect of covariates with a univariate response variable, or to cluster a multivariate outcome. We report simulation results, comparing our approach with the existing techniques. The idea of combining CEC with QRCM permits simplifying computation and interpretation of the results, and may improve the ability to identify clusters. We illustrate a variety of applications, highlighting the advantages and the usefulness of the described method.

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

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

References

  1. Abramowitz M, Stegun I (1964) Handbook of mathematical functions: with formulas, graphs, and mathematical tables, vol 55. Courier Corporation, Chelmsford

    Google Scholar 

  2. Adelfio G, Chiodi M, D’Alessandro A, Luzio D (2011) Fpca algorithm for waveform clustering. J Commun Comput 8(6):494–502

    Google Scholar 

  3. Adelfio G, Chiodi M, D’Alessandro A, Luzio D, D’Anna G, Mangano G (2012) Simultaneous seismic wave clustering and registration. Comput Geosci 44:60–69

    Article  Google Scholar 

  4. Adelfio G, Di Salvo F, Chiodi M (2016) Space-time FPCA algorithm for clustering of multidimensional curves. In: Proceeding of the 48th scientific meeting of the Italian Statistical Society, Salerno

  5. Bouveyron C, Brunet-Saumard C (2014) Model-based clustering of high-dimensional data: a review. Comput Stat Data Anal 71:52–78

    MathSciNet  Article  MATH  Google Scholar 

  6. Clogg C, Petkova E, Haritou A (1995) Statistical methods for comparing regression coefficients between models. Am J Sociol 100(5):1261–1293

    Article  Google Scholar 

  7. Fisher R (1936) The use of multiple measurements in taxonomic problems. Ann Hum Genet 7(2):179–188

    Google Scholar 

  8. Frumento P (2017) QRCM: quantile regression coefficients modeling. https://CRAN.R-project.org/package=qrcm, r package version 2.1

  9. Frumento P, Bottai M (2016) Parametric modeling of quantile regression coefficient functions. Biometrics 72(1):74–84

    MathSciNet  Article  MATH  Google Scholar 

  10. Garcia-Escudero L, Gordaliza A (2005) A proposal for robust curve clustering. J Classif 22(2):185–201

    MathSciNet  Article  MATH  Google Scholar 

  11. Gower J (1975) Generalized procrustes analysis. Psychometrika 40(1):33–51

    MathSciNet  Article  MATH  Google Scholar 

  12. Hotelling H (1933) Analysis of a complex of statistical variables into principal components. J Educ Psychol 24(6):417

    Article  MATH  Google Scholar 

  13. Jacques J, Preda C (2014) Functional data clustering: a survey. Adv Data Anal Classif 8(3):231–255

    MathSciNet  Article  Google Scholar 

  14. James G (2007) Curve alignment by moments. Ann Appl Stat 1:480–501

    MathSciNet  Article  MATH  Google Scholar 

  15. Kneip A, Gasser T (1992) Statistical tools to analyze data representing a sample of curves. Ann Stat 20:1266–1305

    MathSciNet  Article  MATH  Google Scholar 

  16. Koenker R (2005) Quantile regression, vol 38. Cambridge University Press, Cambridge

    Google Scholar 

  17. Koenker R, Bassett G Jr (1978) Regression quantiles. Econom J Econom Soc 46:33–50

    MathSciNet  MATH  Google Scholar 

  18. Pearson K (1901) On lines and planes of closest fit to systems of points in space. In: Proceedings of of the 17th ACM SIGACT-SIGMOD-SIGART symposium on Principles of database systems (SIGMOD)

  19. Ramsay J (2006) Functional data analysis. Wiley, New York

    Google Scholar 

  20. Ramsay J, Li X (1998) Curve registration. J R Stat Soc Ser B 60(2):351–363

    MathSciNet  Article  MATH  Google Scholar 

  21. Sangalli L, Secchi P, Vantini S, Veneziani A (2009) A case study in exploratory functional data analysis: geometrical features of the internal carotid artery. J Am Stat Assoc 104(485):37–48

    MathSciNet  Article  MATH  Google Scholar 

  22. Silverman B (1995) Incorporating parametric effects into functional principal components analysis. J R Stat Soc Ser B 57:673–689

    MathSciNet  MATH  Google Scholar 

  23. Sottile G, Adelfio G (2017) clustEff: clusters of effect curves in quantile regression models. R package version 0.1.1. https://CRAN.R-project.org/package=clustEff

  24. Vichi M, Saporta G (2009) Clustering and disjoint principal component analysis. Comput Stat Data Anal 53(8):3194–3208

    MathSciNet  Article  MATH  Google Scholar 

  25. Wang K, Gasser T (1997) Alignment of curves by dynamic time warping. Ann Stat 25(3):1251–1276

    MathSciNet  Article  MATH  Google Scholar 

Download references

Acknowledgements

We would like to thank the two anonymous reviewers for their suggestions and comments, that allowed us to considerably improve the manuscript.

Funding This paper has been partially supported by the national grant of the Italian Ministry of Education University and Research (MIUR) for the PRIN-2015 program (Progetti di ricerca di Rilevante Interesse Nazionale), “Prot. 20157PRZC4 - Research Project Title Complex space-time modelling and functional analysis for probabilistic forecast of seismic events. PI: Giada Adelfio”.

Author information

Affiliations

  1. Dipartimento di Scienze Economiche Aziendali e Statistiche, University of Palermo, Viale delle Scienze ed. 13, 90128, Palermo, Italy

    Gianluca Sottile & Giada Adelfio

  2. Istituto Nazionale di Geofisica e Vulcanologia, Via Ugo La Malfa, 153, 90146, Palermo, Italy

    Giada Adelfio

Authors
  1. Gianluca Sottile
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Giada Adelfio
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Giada Adelfio.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Sottile, G., Adelfio, G. Clusters of effects curves in quantile regression models. Comput Stat 34, 551–569 (2019). https://doi.org/10.1007/s00180-018-0817-8

Download citation

Keywords

  • Quantile regression coefficients modeling
  • Multivariate analysis
  • Functional data analysis
  • Curves clustering
  • Variable selection