On the Consistency of Kernel Classification Rule for Functional Random Field
[Sur la consistance de la règle de classification du noyau pour le champ aléatoire fonctionnel]
Journal de la société française de statistique, Tome 159 (2018) no. 1, pp. 68-87.

Nous considérons la règle de la fenêtre mobile pour classifier des données fonctionnelles spatialement dépendantes. Nous étudions les propriétés asymptotiques de cette règle de classification non paramétrique basée sur des données d’apprentissage tirées d’un champ aléatoire α ou β - mélangeant à valeurs en espace de dimension infinie. Nous étendons les résultats de Younso (2017a) concernant la consistance et la consistance forte au cas spatialement dépendant sous des hypothèses non restrictives. Nous proposons un critère pour choisir le paramètre de lissage et nous considérons l’application de notre approche sur des données simulées.

We consider the classical moving window rule of classification for functional spatially dependent data. We investigate asymptotic properties of this nonparametric classification rule based on training data drawn from α or β - mixing random field taking values in infinite-dimensional space. We extend the results of Younso (2017a) concerning both the consistency and the strong consistency of the moving window classifier to the spatially dependent case under mild assumptions. We propose a method for bandwidth selection and we conduct some simulation studies.

Keywords: Bayes rule, training data, moving window rule, random field, bandwidth, consistency
Mot clés : Règle de Bayes, données d’apprentissage, règle de fenêtre mobile, champ aléatoire, paramètre de lissage, consistance
@article{JSFS_2018__159_1_68_0,
     author = {Younso, Ahmad},
     title = {On the {Consistency} of {Kernel} {Classification} {Rule} for {Functional} {Random} {Field}},
     journal = {Journal de la soci\'et\'e fran\c{c}aise de statistique},
     pages = {68--87},
     publisher = {Soci\'et\'e fran\c{c}aise de statistique},
     volume = {159},
     number = {1},
     year = {2018},
     mrnumber = {3803124},
     zbl = {1397.62358},
     language = {en},
     url = {http://archive.numdam.org/item/JSFS_2018__159_1_68_0/}
}
TY  - JOUR
AU  - Younso, Ahmad
TI  - On the Consistency of Kernel Classification Rule for Functional Random Field
JO  - Journal de la société française de statistique
PY  - 2018
SP  - 68
EP  - 87
VL  - 159
IS  - 1
PB  - Société française de statistique
UR  - http://archive.numdam.org/item/JSFS_2018__159_1_68_0/
LA  - en
ID  - JSFS_2018__159_1_68_0
ER  - 
%0 Journal Article
%A Younso, Ahmad
%T On the Consistency of Kernel Classification Rule for Functional Random Field
%J Journal de la société française de statistique
%D 2018
%P 68-87
%V 159
%N 1
%I Société française de statistique
%U http://archive.numdam.org/item/JSFS_2018__159_1_68_0/
%G en
%F JSFS_2018__159_1_68_0
Younso, Ahmad. On the Consistency of Kernel Classification Rule for Functional Random Field. Journal de la société française de statistique, Tome 159 (2018) no. 1, pp. 68-87. http://archive.numdam.org/item/JSFS_2018__159_1_68_0/

[1] Abraham, C.; Biau, G.; Cadre, B. On the kernel rule for function classification, Ann. Inst. Statist. Math., Volume 58 (2006), pp. 619-633 | MR | Zbl

[2] Biau, G.; Cadre, B. Nonparametric spatial prediction, Statistical Inference for Stochastic Processes, Volume 7 (2004), pp. 327-349 | MR | Zbl

[3] Berbee, H.C.P. Random walks with stationary increments and renewal theory, Math. Cent. Tracts. Amsterdam, Volume 58 (1979) | MR | Zbl

[4] Bosq, D. Nonparametric Statistics for Stochastic Processes, Springer-Verlag, New York, 1998 | MR | Zbl

[5] Bradley, R. C. Approximation theorems for strongly mixing random variables, Michigan Math. J., Volume 30 (1983), pp. 69-81 | MR | Zbl

[6] Cérou, F.; Guyader, A. Nearest neighbor classification in infinite dimension, ESAIM: Probability and Statistics, Volume 10 (2006), pp. 340-355 | Numdam | MR | Zbl

[7] Carbon, M.; Tran, L.T.; Wu, B. Kernel density estimation for random fields (density estimation for random fields), Statistics & Probability Letters, Volume 36 (1997), pp. 115-125 | MR | Zbl

[8] Devroye, L.; Györfi, L.; Lugosi, G. A probabilitic Theory of Pattern Recognition, Springer-Verlag, New York, 1996 | MR | Zbl

[9] Devroye, L.; Krzyżak, A. An equivalence theorem for L1 convergence of the kernel regression estimate, Journal of statistical planning and Inference, Volume 23 (1989), pp. 71-82 | MR | Zbl

[10] Doukhan, P.; Massart, P.; Rio, E. Invariance principles for absolutely regular empirical processes, Ann. Inst. H. Poincaré Probab. Statist., Volume 31 (1995), pp. 393-427 | Numdam | MR | Zbl

[11] Dabo-Niang, S.; Rachdi, M.; Yao, A. F. Kernel regression estimation for spatial functional random variables, Far East Journal of Theoretical Statistics, Volume 32 (2011), pp. 77-113 | MR | Zbl

[12] Dabo-Niang, S.; Yao, A. F. Kernel regression estimation for continuous spatial processes, Mathematical Methods of Statistics, Volume 16 (2007), pp. 298-317 | MR | Zbl

[13] Dabo-Niang, S.; Yao, A. F. Kernel spatial density estimation in infinite dimension space, Metrika, Volume 76 (2013), pp. 19-52 | MR | Zbl

[14] El-Machkouri, M. Nonparametric regression estimation for random fields in a fixed-design, Statistical Inference for Stochastic Processes, Volume 10 (2007), pp. 29-47 | MR | Zbl

[15] Febrero-Bande, M.; de la Fuente, M. Oviedo Statistical computing in functional data analysis: The R package fda.usc., Journal of statistical Software, Volume 51 (2012)

[16] Ferraty, F.; Keilegom, I. Van; Vieu, P. The functional nonparametric model and application to spectrometric data, Comput. Statist., Volume 17 (2002), pp. 54-564 | MR | Zbl

[17] Ferraty, F.; Keilegom, I. Van; Vieu, P. Regression when both response and predictor are functions, J. Multivariate Anal., Volume 109 (2012), pp. 10-28 | MR | Zbl

[18] Ferraty, F.; Vieu, P. Curves discrimination : a nonparametric approach, Computational Statistics and Data Analysis, Volume 44 (2003), pp. 161-173 | MR | Zbl

[19] Ferraty, F.; Vieu, P. Nonparametric functional data analysis, Springer-Verlag, New York, 2006 | MR | Zbl

[20] Hallin, M.; Lu, Z.; Tran, L.T. Local linear spatial regression, The Annals of Statistics, Volume 32 (2004), pp. 2469-2500 | MR | Zbl

[21] Hallin, M.; Lu, Z.; Yu, K. Local linear spatial quantile regression, The Annals of Statistics, Volume 15 (2009), pp. 659-686 | MR | Zbl

[22] Jacques, J.; Preda, C. Model-based clustering for multivariate functional data, Computational Statistics and Data Analysis, Volume 71 (2014), pp. 92-106 | MR | Zbl

[23] Kechris, A. S. Classical descriptive set theory, Springer-Verlag, New York, 1995 | MR | Zbl

[24] Kulkarni, S. R.; Posner, S. E. Rate of convergence of nearest neighbor estimation under arbitrary sampling, IEEE Transactions on Information Theory, Volume 41 (1995), pp. 1028-1039 | MR | Zbl

[25] Kolmogorov, A. N.; Tihomirov, V. M. ϵ -entropy and ϵ -capacity of sets in functional spaces, American Mathematical Society Translations, Volume 17 (1961), pp. 277-364 | MR | Zbl

[26] McDiarmid, C. On the method of bounded differences, in Surveys in Combinatorics, Cambridge University Press, Cambridge, Volume 794 (1989), pp. 261-283 | MR | Zbl

[27] Nadaraya, E.A. On estimating regression, Theory of probability and its applications, Volume 9 (1989), pp. 141-142 | Zbl

[28] Neaderhouser, C. C. Convergence of block spins defined on random fields, J. Statist. Phys., Volume 22 (1980), pp. 673-684 | MR

[29] Parzen, E. On estimation of a probability density function and mode, Ann. Math. Statist., Volume 33 (1962), pp. 1065-1076 | MR | Zbl

[30] Preda, C. Regression models for functional data by reproducing kernel hilbert spaces methods, Journal of Statistical Planning and Inference, Volume 137 (2007), pp. :829-840 | MR | Zbl

[31] Rio, E. Théorie asymptotique des processus aléatoires faiblement dépendants. Mathématiques et Applications, Springer, Berlin, 2000 | MR | Zbl

[32] Rosenblatt, M. A central limit theorem and a strong mixing condition, Proc. Nat. Acad. Sci., USA, Volume 42 (1956), pp. 43-47 | MR | Zbl

[33] Rosenblatt, M. Stationary sequences and random fields, Birkhauser, Boston, 1985 | MR | Zbl

[34] Ramsay, J.O.; Silverman, B.W. Applied Functional Data Analysis, Methods and Case Studies, Springer-Verlag, New York, 2002 | MR

[35] Ramsay, J.O.; Silverman, B.W. Functional Data Analysis, Springer-Verlag, Springer Series in Statistics, second edition, 2005 | MR | Zbl

[36] Rachdi, M.; Vieu, P. Nonparametric regression for functional data: automatic smoothing parameter selection, Journal of Statistical Planning and Inference, Volume 137 (2007), pp. 2784-2801 | MR | Zbl

[37] Rozanov, Y. A.; Volkonskii, V.A. Some limit theorems for random functions, I. Teor. Veroyatn. Primen., Volume 4 (1959), pp. 186-207 | MR | Zbl

[38] Stone, C. J. Consistent nonparametric regression, The Annals of Statistics, Volume 5 (1977), pp. 595-620 | MR | Zbl

[39] Ternynck, C. Spatial regression estimation for functional data with spatial dependency, Journal de la Société Française de Statistique, Volume 155 (2014), pp. 138-160 | Numdam | MR | Zbl

[40] Tran, L.T. Kernel density estimation on random fields, Journal of Multivariate Analysis, Volume 34 (1990), pp. 37-53 | MR | Zbl

[41] Viennet, G. Inequalities for absolutely sequence. Application to density estimation , Probability Theory and Related Fields, Volume 107 (1967), pp. 467-492 | MR | Zbl

[42] Watson, G.S. Smooth regression analysis, Sankhy a Ser. A, Volume 26 (1964), pp. 359-372 | MR | Zbl

[43] Younso, A. On nonparametric classification for weakly dependent functional processes, ESAIM: Probability and Statistics. https://doi.org/10.1051/ps/2017002 (2017) | MR | Zbl

[44] Younso, A. On the consistency of a new kernel rule for spatially dependent data, Statistics & Probability Letters, Volume 131 (2017), pp. 64-71 | MR | Zbl