Skip to main content
SpringerLink
Log in

Component-wise outlier detection methods for robustifying multivariate functional samples

  • Regular Article
  • Published:
Statistical Papers Aims and scope Submit manuscript

Abstract

We propose a new method for detecting outliers in multivariate functional data. We exploit the joint use of two different depth measures, and generalize the outliergram to the multivariate functional framework, aiming at detecting and discarding both shape and magnitude outliers. The main application consists in robustifying the reference samples of data, composed by G different known groups to be used, for example, in classification procedures in order to make them more robust. We asses by means of a simulation study the method’s performance in comparison with different outlier detection methods. Finally we consider a real dataset: we classify data minimizing a suitable distance from the center of reference groups. We compare performance of supervised classification on test sets training the algorithm on original dataset and on the robustified one, respectively.

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

Similar content being viewed by others

References

  • Arribas-Gil A, Romo J (2014) Shape outlier detection and visualization for functional data: the outliergram. Biostatistics 15(4):603–619

    Article  Google Scholar 

  • Berrendero J, Justel A, Svarc M (2011) Principal components for multivariate functional data. Comput Stat Data Anal 55(9):2619–2634. doi:10.1016/j.csda.2011.03.011

    Article  MathSciNet  MATH  Google Scholar 

  • Claeskens G, Hubert M, Slaets L, Vakili K (2014) Multivariate functional halfspace depth. J Am Stat Assoc 109(505):411–423

    Article  MathSciNet  Google Scholar 

  • Cuesta-Albertos JA, Febrero-Bande M, Oviedo de la Fuente M (2016) The dd\(^g\)-classifier in the functional setting. TEST 1:1–24. doi:10.1007/s11749-016-0502-6

    Article  MATH  Google Scholar 

  • Febrero-Bande M, Galeano P, González-Manteiga W (2008) Outlier detection in functional data by depth measures, with application to identify abnormal no\(_x\) levels. Environmetrics 19(4):331–345

    Article  MathSciNet  Google Scholar 

  • Gervini D (2008) Robust functional estimation using the median and spherical principal components. Biometrika 95(3):587–600

    Article  MathSciNet  Google Scholar 

  • Hawkins DM (1980) Identification of outliers. Springer, New York

    Book  Google Scholar 

  • Hodge V, Austin J (2004) A survey of outlier detection methodologies. Artif Intell Rev 22(2):85–126

    Article  Google Scholar 

  • Hubert M, Vandervieren E (2008) An adjusted boxplot for skewed distributions. Comput Stat Data Anal 52:5186–5201

    Article  MathSciNet  Google Scholar 

  • Hubert M, Rousseeuw P, Segaert P (2015) Multivariate functional outlier detection. Stat Methods Appl 24(2):177–202

    Article  MathSciNet  Google Scholar 

  • Hubert M, Rousseeuw P, Segaert P (2016) Multivariate and functional classification using depth and distance. Adv Data Anal Classif 1:1–22

    MATH  Google Scholar 

  • Hyndman R, Shang H (2010) Rainbow plots, bagplots, and boxplots for functional data. J Comput Graph Stat 19:29–45

    Article  MathSciNet  Google Scholar 

  • Ieva F, Paganoni AM (2013) Depth measures for multivariate functional data. Commun Stat Theory Methods 42(7):1265–1276

    Article  MathSciNet  Google Scholar 

  • Ieva F, Paganoni A, Pigoli D, Vitelli V (2013) Multivariate functional clustering for the morphological analysis of ecg curves. J R Stat Soc Ser C (Appl Stat) 62(3):401–418

    Article  MathSciNet  Google Scholar 

  • Indino F (2015) Analisi statistica di dati ad alta dimensionalit : un’applicazione ai segnali elettrocardiografici. Master’s thesis, Politecnico di Milano, URL https://www.politesi.polimi.it/handle/10589/107284

  • Kraus D, Panaretos VM (2012) Dispersion operators and resistant second-order functional data analysis. Biometrika 99(4):813–832

    Article  Google Scholar 

  • Kuhnt S, Rehage A (2016a) An angle-based multivariate functional pseudo-depth for shape outlier detection. J Multivar Anal 146:325–340

    Article  MathSciNet  Google Scholar 

  • Kuhnt S, Rehage A (2016b) An angle-based multivariate functional pseudo-depth for shape outlier detection. J Multivar Anal 146:325–340

    Article  MathSciNet  Google Scholar 

  • Li J, Cuesta-Albertos J, Dd-classifier LRY (2012) Nonparametric classification procedure based on dd-plot. J Am Stat Assoc 107:737–753

    Article  MathSciNet  Google Scholar 

  • Lopez-Pintado S, Romo J (2009) On the concept of depth for functional data. J Am Stat Assoc 104(486):718–734

    Article  MathSciNet  Google Scholar 

  • Lopez-Pintado S, Romo J (2011) A half-region depth for functional data. Comput Stat Data Anal 55:1679–1695

    Article  MathSciNet  Google Scholar 

  • Lopez-Pintado S, Sun Y, Genton M (2014) Simplicial band depth for multivariate functional data. Adv Data Anal Classif 8:321–338

    Article  MathSciNet  Google Scholar 

  • Mosler K, Mozharovskyi P (2015) Fast dd-classification of functional data. Stat Pap. doi:10.1007//s00362-015-0738-3

    Article  MATH  Google Scholar 

  • Paindaveine D, Bever GV (2015) Discussion of multivariate functional outlier detection, by mia hubert, peter rousseeuw and pieter segaert. Stat Methods Appl 24:223–231

    Article  MathSciNet  Google Scholar 

  • R Core Team (2013) R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. http://www.R-project.org/. ISBN 3-900051-07-0

  • Ramsay J, Silverman B (2005) Functional data analysis, 2nd edn. Springer, New York

    Book  Google Scholar 

  • Rehage A (2016) FUNTA: Functional Tangential Angle Pseudo-Depth, https://CRAN.R-project.org/package=FUNTA. R package version 0.1.0

  • Sun Y, Genton M (2012) Adjusted functional boxplots for spatio-temporal data visualization and outlier detection. Environmetrics 23(1):53–64

    Article  MathSciNet  Google Scholar 

  • Tarabelloni N, Ieva F (2016) On data robustification in functional data analysis. MOX Report 03/2016, Department of Mathematics - Politecnico di Milano, https://www.mate.polimi.it/biblioteca/add/qmox/03-2016.pdf

  • Tarabelloni N, Ieva F, Biasi R, Paganoni A (2015) Use of depth measure for multivariate functional data in disease prediction: an application to electrocardiographic signals. Int J Biostat, (To appear)

  • Tarabelloni N, Arribas-Gil A, Ieva F, Paganoni AM, Romo J (2016) roahd: Robust Analysis of High Dimensional Data. https://CRAN.R-project.org/package=roahd. R package version 1.0

Download references

Author information

Authors and Affiliations

  1. MOX - Department of Mathematics, Politecnico di Milano, via Bonardi 9, 20133, Milan, Italy

    Francesca Ieva & Anna Maria Paganoni

Authors
  1. Francesca Ieva
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Anna Maria Paganoni
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anna Maria Paganoni.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ieva, F., Paganoni, A.M. Component-wise outlier detection methods for robustifying multivariate functional samples. Stat Papers 61, 595–614 (2020). https://doi.org/10.1007/s00362-017-0953-1

Download citation

  • Received:

  • Revised:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00362-017-0953-1

Keywords

Search

Navigation