Strong consistency of the mode of multivariate recursive kernel density estimator under strong mixing hypothesis

Fatma Ben Khadher ; Yousri Slaoui

Teoriâ slučajnyh processov, Tome 25 (2020) no. 2, pp. 61-73.

Résumé

In this research paper, we define a kernel estimator of the mode based on the recursive kernel density estimator developed by [23]. In addition, we establish its almost sure convergence under strong mixing hypothesis. Finally, we corroborate these theoretical results through numerical simulations.

Détail

Keywords: Nonparametric estimation, Density estimation, Stochastic approximation, Strong mixing, Strong consistency.
Mots-clés : Mode

Bibliographie

[1] J. R. Blum, D. L. Hanson, L. H. Koopmans, “On the strong law of large numbers for a class of stochastic processes”, Z. Wahrsch. Ver. Geb., 2 (1963), 1–11

[2] D. Bosq, Nonparametric statistics for stochastic processes: estimation and prediction, Springer, New York, 1999

[3] S. Boukabour, A. Masmoudi, “Semiparametric Bayesian networks for continuous data”, Comm. Statist. Theory Methods, 2020

[4] R. Bradley, Introduction to strong mixing conditions, Kendrick Press, Heber City, 2007

[5] Y. Cheng, “Mean shift, mode seeking, and clustering”, IEEE Trans. Pattern Anal. Mach. Intell., 17 (1995), 790–799

[6] H. Chernoff, “Estimation of the mode”, Ann. Inst. Statist. Math., 16 (1964), 31–41

[7] G. Collomb, W. Hardle, S. Hassani, “A note on prediction via estimation of the conditional mode function”, J. Statist. Plann. Inference, 15 (1987), 227–236

[8] J. Dedecker, P. Doukhan, G. Lang, J. R. Leon, S. Louhichi, C. Prieur, Weak dependence with examples and applications, Springer, Berlin, 2007

[9] P. Doukhan, Mixing: properties and examples, Springer, New York, 1994

[10] W. F. Eddy, “Optimum kernel estimators of the mode”, Ann. Statist., 8 (1980), 870–882

[11] W. F. Eddy, “The asymptotic distributions of kernel estimators of the mode”, Probab. Theory Related Fields, 59 (1982), 279–290

[12] A. Gannoun, D. Louani, “Asymptotic properties of kernel estimators of the mode under censoring”, Technical Report University of Montpellier 11, 9 (1996), 96–04

[13] S. B. Hedges, P. Shah, “Comparison of mode estimation methods and application in molecular clock analysis”, BMC bioinformatics, 4:31 (2003)

[14] H. O. Hirschfeld, “A connection between correlation and contingency”, Math. Proceed. of the Cambridge Philosophical Soc, 31 (1935), 520–524

[15] M. W. Hofbaur, B. C. Williams, “Mode estimation of probabilistic hybrid systems”, In International Workshop on Hybrid Systems: Computation and Control (HSCC), 2002, 253–266

[16] I. A. Ibragimov, “Some limit theorems from stationary processes”, Theory Proc. Appl., 7 (1962), 349–382

[17] H. Jiang, S. Kpotufe, Modal-set estimation with an application to clustering, 2016, arXiv: : 04166, 2016

[18] A. N. Kolmogorov, “Uber die analytischen methoden inder wahrschein lichkeitsrechnung”, Math. Ann., 104 (1931), 415–458

[19] V. D. Konakov, “On the asymptotic normality of the mode of multidimensional distributions”, Theory Probab. Appl., 19 (1974), 794–799

[20] D. Louani, “On the asymptotic normality of the kernel estimators of the density function and its derivatives under censoring”, Comm. Statist. Theory Methods, 27 (1998), 2909–2924

[21] D. Louani, E. Ould Saïd, “Asymptotic normality of kernel estimators of the conditional mode under strong mixing hypothesis”, J. Nonparametr. Stat., 11 (1999), 413–442

[22] E. Masry, “Recursive probability density estimation for weakly dependent process”, IEEE Trans. Inform. Theory, 32 (1986), 254–267

[23] A. Mokkadem, M. Pelletier, Y. Slaoui, “The stochastic approximation method for the estimation of a multivariate probability density”, J. Statist. Plann. Inference, 139 (2009), 2459–2478

[24] E. N. Nadaraya, “On nonparametric estimates of density functions and regression curves”, Theory Probab. Appl., 10 (1965), 186–190

[25] E. Ould Saïd, “Estimation non paramétrique du mode conditionnel application ѓya la prévision”, C. R. Math. Acad. Sci. Paris, 316 (1993), 943–947

[26] E. Ould Saïd, “Strong uniform consistency of nonparametric estimation of the censored conditional mode function”, J. Nonparametr. Stat., 17 (2005), 797–806

[27] E. Parzen, “On estimation of a probability density function and mode”, Ann. Math. Statist., 33 (1962), 1065–1076

[28] P. Révész, “Robbins-Monro procedure in a Hilbert space and its application in the theory of learning processes I”, Studia Sci. Math. Hung., 8 (1973), 391–398

[29] P. Révész, “How to apply the method of stochastic approximation in the non-parametric estimation of a regression function”, Math. Operationsforsch. Statist., Ser. Statistics., 8 (1977), 119–126

[30] E. Rio, Théorie asymptotique des processus aléatoires faiblement dépendants. Mathématiques et applications, Springer, New York, 2000

[31] J. P. Romano, “On weak convergence and optimality of kernel density estimates of the mode”, Ann. Statist., 16 (1988), 629–647

[32] M. Rosenblatt, “A central limit theorem and a strong mixing condition”, Proc. Natl. Acad. Sci. USA, 42 (1956), 43–47

[33] M. Rosenblatt, “Remarks on some nonparametric estimates of a density function”, Ann. Math. Statist., 27 (1956), 832–837

[34] M. Samanta, “Nonparametric estimation of the mode of a multivariate density”, South African Statist. J., 7 (1973), 109–117

[35] S. A. Nezam Sarmadi, V. Venkatasubramanian, “Electromechanical mode estimation using recursive adaptive stochastic subspace identification”, IEEE Trans. Power Syst., 29 (2014), 349–358

[36] Y. A. Sheikh, E. A. Khan, T. Kanade, “Mode-seeking by medoidshifts”, Proc. 11th IEEE Internat. Conf. on Computer Vision, 2007, 1–8

[37] Y. Slaoui, “Large and moderate principles for recursive kernel density estimators defined by stochastic approximation method”, Serdica Math. J., 39 (2013), 53–82

[38] Y. Slaoui, “Bandwidth selection for recursive kernel density estimators defined by stochastic approximation method”, J. Probab. Stat, 2014

[39] Y. Slaoui, “Bias reduction in kernel density estimation”, J. Nonparametr. Stat., 30 (2018), 505–522

[40] Y. Slaoui, “Recursive nonparametric regression estimation for independent functional data”, Statist. Sinica, 30 (2020), 417–437

[41] W. Tao, H. Jin, Y. Zhang, “Colour image segmentation based on mean shift and normalized cuts”, IEEE Trans. Syst., Man, Cybern. B, Cybern., 37 (2007), 1382–1389

[42] A. B. Tsybakov, “Recurrent estimation of the mode of a multidimensional distribution”, Probl. Inf. Transm., 8 (1990), 119–126

[43] J. Van Ryzin, “On strong consistency of density estimates”, South African Statist. J., 40 (1969), 1765–1772

[44] P. Vieu, “A note on density mode function”, Statist. Probab. Lett., 26 (1996), 297–307

[45] B. Williams, S. Chung, V. Gupta, “Mode estimation of model-based programs: monitoring systems with complex behavior”, In Proc. Int. Joint Conf. Artif. Intell. (IJCAI), 2001, 579–590

[46] P. Yin, H.-Y. Tourapis, A. Tourapis, J. Boyce, “Fast mode decision and motion estimation for JVT/H.264”, Proceedings of IEEE International Conference on Image Processing, 2003, 853–856