LIMIT LAWS OF FUNCTIONAL k-NEAREST NEIGHBORS CONDITIONAL MODE ESTIMATE
Abstract
This research study the k-Nearest Neighbors (k-NN) of the conditional mode by using the local linear technique in the case of a scalar response variable that are linked via a single-index structure. The main contribution of this work is to investigate the asymptotic normality of the nonparametric estimator of the conditional mode under some general assumptions. A simulation study was conducted to assess finite sample behavior to exhibit the eectiveness of our method over the standard kernel method.
Keywords
Full Text:
PDFReferences
bibitem{12}{sc A. Ait-Sa"{i}di, F. Ferraty, R. Kassa, {rm and} P. Vieu}: textit{Cross-validated estimations in the single-functional index model.} Statistics . textbf{42}, (2008), 475-494.
bibitem{sss1}{ sc I. Almanjahie, Z. Kaid, A. Laksaci, {rm and} M. Rachdi}:textit{ Predicting temperature curve based on fast kNN local linear estimation of the conditional distribution function}. PeerJ . textbf{9},(2021), pp. e11719 .
bibitem{d2021} {sc I. Almanjahie, W. Alahmari, A. Laksaci, {rm and} M. Rachdi}: textit{Computational aspects of the k NN local linear smoothing for some conditional models in high dimensional statistics.} Communications In Statistics-Simulation And Computation. (2021), pp. 1-32.
bibitem{d2022}{ sc I. Almanjahie, K. A . Assiri, A. Laksaci, Z. Chikr Elmezouar} textit{ The k nearest neighbors smoothing of the relative-error regression with functional regressor,} Commun. Stat. Theory Methods, textbf{51}. (2022), 4196–4209. https://doi.org/10.1080/03610926.2020.1811870.
bibitem {d20222} { sc İ. Almanjahie , W. Mesfer and L. Ali }, textit{ The k nearest neighbors local linear estimator of functional conditional density when there are missing data}, Hacettepe Journal of Mathematics and Statistics, textbf{ 51} , (2022) no. 3, pp. 914-931.
bibitem{alshahrani2023knn} { sc F. Alshahrani, W. Bouabsa, I. Almanjahie {rm and} M. Kadi, } textit{ kNN local linear estimation of the conditional density and mode for functional spatial high dimensional data.} AIMS Mathematics. textbf{8}, (2023), 15844-15875.
bibitem{Ab}{sc S. Attaoui, {rm and} N. Ling} : textit{Asymptotic results of a nonparametric conditional cumulative distribution estimator in the single functional index modeling for time series data with applications}. Metrika. textbf{79}, (2016), 485-511.
bibitem{AB12}{sc M. Attouch {rm and} B. Tawfik}: textit{Asymptotic distribution of robust k-nearest neighbour estimator for functional nonparametric models}. Matematichki Vesnik. textbf{64}, (2012), 275-285.
bibitem{bo} {sc O. Bouanani, A. Laksaci, M. Rachdi {rm and} S. Rahmani} : textit{Asymptotic normality of some conditional nonparametric functional parameters in high-dimensional statistics}. Behaviormetrika. textbf{46} ,(2019), pp. 199-233.
bibitem{booo} {sc O. Bouanani, S. Rahmani, A. Laksaci, {rm and}M. Rachdi }:textit{ Asymptotic normality of conditional mode estimation for functional dependent data}. Indian Journal Of Pure And Applied Mathematics . textbf{51}, (2020), 465-481.
bibitem{3} {sc D. Bosq}textit{ Linear processes in function spaces: theory and applications}. (Springer Science and Business Media, (2000).
bibitem{k1} {sc F. Burba, F. Ferraty {rm and} P. Vieu} textit{k-Nearest Neighbour method in functional nonparametric regression.} Journal Of Nonparametric Statistics. textbf{21}, (2009), 453-469.
bibitem{CA06} {sc F. C'{e}rou, {rm and} A. Guyader}: textit{Nearest neighbor classification in infinite dimension}. ESAIM: PS. textbf{10}, (2006), pp. 340-355.
bibitem{d1d} {sc Z. Chikr-Elmezouar, I.M. Almanjahie, A. Laksaci {rm and} M. Rachdi}:textit{ FDA: strong consistency of the kNN local linear estimation of the functional conditional density and mode}. Journal of Nonparametric Statistics. textbf{31}(1), (2019), 175-195.
bibitem{C80} {sc G. Collomb}: textit{ Estimation de la r'{e}gression par la m'{e}thode des k points les plus proches avec noyau: quelques propri'{e}t'{e}s de convergence ponctuelle}. Nonparametric Asymptotic Statistics (Proc. Conf., Rouen, 1979) (French). textbf{821}, (1980), pp. 159-175.
bibitem{Dabo12H} {sc S. Dabo-Niang, Z. Kaid, {rm and} A. Laksaci} textit{ On spatial conditional mode estimation for a functional regressor}. Statist. Probab. Lett. , {bf 82},(2012), 1413-1421.
bibitem{Demongeot11} {sc J. Demongeot, A. Laksaci , F. Madani, {rm and} M. Rachdi}: textit{Functional data: local linear estimation of the conditional density and its application,} textit{ Statistics.} {bf47}, (2013), 26-44.
bibitem{1} {sc J. Dauxois, A. Pousse, {rm and} Y. Romain}: textit{Asymptotic theory for the principal component analysis of a vector random function: some applications to statistical inference}. Journal Of Multivariate Analysis . textbf{12},(1982), 136-154.
bibitem{F} {sc J. Fan}: textit{Local Polynomial Modelling and Its Applications}. Pub. Location Boca Raton, 1996.
bibitem{101} {sc J. Fan, {rm and} I. Gijbels}textit{ Local polynomial modelling and its applications: monographs on statistics and applied probability} 66. (Routledge,2018).
bibitem{10}{sc F. Ferraty, A. Peuch, {rm and} P. Vieu}: textit{Modèle à indice fonctionnel simple}. Comptes Rendus Mathematique. textbf{336}, (2003), 1025-1028
bibitem{FLV05H}{sc F. Ferraty, A. Laksaci, {rm and} F. Vieu}: textit{ Functional time series
prediction via the conditional mode estimation.} C. R., Math., Acad. Sci. Paris, {bf 340}, (2005), 389-392.
bibitem{Fes} {sc F. Ferraty {rm and } P. Vieu}. textit{ Nonparametric functional data analysis}. Springer, New York, Theory and practice, 2006
bibitem{15} {sc A. Goia, {rm and} P. Vieu,} textit{A partitioned single functional index model}. Computational Statistics. textbf{30}, (2015), 673-692
bibitem{KLOH} {sc S. Khardani, M. Lemdani, {rm and} E. Ould-Sa"{i}d}: textit{Uniform rate of
strong consistency for a smooth kernel estimator of the conditional
mode for censored time series}. J. Statist. Plann. Inference , {bf 141}, (2011), 3426-3436.
bibitem{R}{sc M. Rachdi, A. Laksaci, J. Demongeot, A. Abdali {rm and} F. Madani} textit{Theoretical and practical aspects of the quadratic error in the local linear estimation of the conditional density for functional data}. Comput. Stat. Data Anal. textbf{73},(2014), pp. 53-68.
bibitem{OT11H} { sc E. Ould-Sa"{i}d and Tatachak, A.} A nonparametric conditional mode estimate under RLT model and strong mixing condition. {em Int. J. Stat. Econ.}, {bf 6}, 76-92. (2011)
bibitem{L} {sc A. Laksaci, F. Madani {rm and} M. Rachdi}: textit{Kernel conditional density estimation when the regressor is valued in a semi-metric space}. Communcations in Statistics-Theory and Methods. textbf{42}(19),( 2013), 3544-3570.
bibitem{102} {sc A. Laksaci, M. Rachdi {rm and} S. Rahmani}: textit{Spatial modelization: local linear estimation of the conditional distribution for functional data.} Spatial Statistics. textbf{6} ,(2013), pp. 1-23.
bibitem{16} {sc N. Ling, {rm and} Q. Xu}:textit{ Asymptotic normality of conditional density estimation in the single index model for functional time series data}. Statistics and Probability Letters . textbf{82}, (2012), 2235-2243.
bibitem{2022m} {sc M. Mohammedi, S. Bouzebda, A. Laksaci {rm and} O. Bouanani} textit{ Asymptotic normality of the k-NN single index regression estimator for functional weak dependence data}, Communications in Statistics - Theory and Methods,(2022), DOI: 10.1080/03610926.2022.2150823
bibitem{MD11} {sc S. Muller, {rm and} J. Dippon}textit{ k-NN kernel estimate for nonparametric functional regression in time series analysis. } Fachbereich Mathematik, Fakultat Mathematik Und Physik (Pfaffenwaldring 57) . textbf{14},(2011), pp. 2011.
bibitem{2} {sc J. Ramsay, {rm and} B. Silverman} . textit{Functional Data Analysis Springer-Verlag.} New York . (1997)
bibitem{100} {sc D. Ruppert, {rm and} M. Wand} textit{Multivariate locally weighted least squares regression.} The Annals Of Statistics. (1994), pp. 1346-1370
bibitem{17} {sc P. Sang, {rm and} J. Cao}: textit{Functional single-index quantile regression models}. Statistics And Computing, (2020), pp. 1-11
DOI: https://doi.org/10.22190/FUMI220322030B
Refbacks
- There are currently no refbacks.
ISSN 0352-9665 (Print)