×

Simplicial band depth for multivariate functional data. (English) Zbl 1414.62066

Summary: We propose notions of simplicial band depth for multivariate functional data that extend the univariate functional band depth. The proposed simplicial band depths provide simple and natural criteria to measure the centrality of a trajectory within a sample of curves. Based on these depths, a sample of multivariate curves can be ordered from the center outward and order statistics can be defined. Properties of the proposed depths, such as invariance and consistency, can be established. A simulation study shows the robustness of this new definition of depth and the advantages of using a multivariate depth versus the marginal depths for detecting outliers. Real data examples from growth curves and signature data are used to illustrate the performance and usefulness of the proposed depths.

MSC:

62F07 Statistical ranking and selection procedures
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)

Software:

fda (R); AS 307
PDF BibTeX XML Cite
Full Text: DOI

References:

[1] Apanasovich, TV; Genton, MG; Sun, Y., A valid Matérn class of cross-covariance functions for multivariate random fields with any number of components, J Am Stat Assoc, 107, 180-193, (2012) · Zbl 1261.62087
[2] Cheng A, Ouyang M (2001) On algorithms for simplicial depth. In: Proceeding 13th Canadian conference on computational geometry, vol 1, pp 53-56
[3] Cuevas, A.; Febrero, M.; Fraiman, R., Robust estimation and classification for functional data via projection-based depth notions, Comput Stat, 22, 481-496, (2007) · Zbl 1195.62032
[4] Ferraty F, Vieu P (2006) Nonparametric Functional Data Analysis. Springer, New York · Zbl 1119.62046
[5] Fraiman, R.; Muniz, G., Trimmed means for functional data, Test, 10, 419-440, (2001) · Zbl 1016.62026
[6] Genton, MG; Johnson, C.; Potter, K.; Stenchikov, G.; Sun, Y., Surface boxplots, Stat, 3, 1-11, (2014)
[7] Gervini, D., Outlier detection and trimmed estimation for general functional data, Statistica Sinica, 22, 1639-1660, (2012) · Zbl 1253.62019
[8] Gneiting, T.; Kleiber, W.; Schlather, M., Matérn cross-covariance functions for multivariate random fields, J Am Stat Assoc, 105, 1167-1177, (2010) · Zbl 1390.62194
[9] Ieva, F.; Paganoni, M., Depth measures for multivariate functional data, Commun Stat, 42, 1265-1276, (2013) · Zbl 1347.62093
[10] Liu, RY, On a notion of data depth based upon random simplices, Ann Stat, 18, 405-414, (1990) · Zbl 0701.62063
[11] López-Pintado, S.; Jörnsten, R., Functional data analysis via extensions of the band depth, IMS lecture Notes-Monograph Series, Inst Math Stat, 54, 103-120, (2007)
[12] López-Pintado, S.; Romo, J., Depth-based inference for functional data, Comput Stat Data Anal, 51, 4957-4968, (2007) · Zbl 1162.62359
[13] López-Pintado S, Romo J (2009) On the concept of depth for functional data. J Am Stat Assoc 104(486): 718-734 · Zbl 1388.62139
[14] López-Pintado, S.; Wei, Y.; Ferraty, F. (ed.), Depth for sparse functional data, 209-212, (2011), Berlin
[15] Matérn B (1960) Spatial variation. Springer, New York
[16] Ramsay JO, Hooker G, Graves S (2009) Functional data analysis with R and MATLAB. Springer, New York · Zbl 1179.62006
[17] Ramsay JO, Silverman BW (2005) Functional data analysis, 2nd edn. Springer, New York
[18] Rousseeuw PJ, Ruts I (1996) Bivariate location depth. Appl Stat 45:516-526 · Zbl 0905.62002
[19] Stein ML (1999) Interpolation of spatial data: some theory for Kriging. Springer, Berlin · Zbl 0924.62100
[20] Sun, Y.; Genton, MG, Functional boxplots, J Comput Grap Stat, 20, 313-334, (2011)
[21] Sun, Y.; Genton, MG, Adjusted functional boxplots for spatio-temporal data visualization and outlier detection, Environmetrics, 23, 54-64, (2012)
[22] Sun, Y.; Genton, MG, Functional median polish, J Agric Biol Environ Stat, 17, 354-376, (2012) · Zbl 1302.62281
[23] Sun, Y.; Genton, MG; Nychka, D., Exact fast computation of band depth for large functional datasets: how quickly can one million curves be ranked?, Stat, 1, 68-74, (2012)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.