A large deviation inequality for -mixing time series and its applications to the functional kernel regression model

DOI10.1016/J.SPL.2017.09.013MaRDI QIDQ680473zbMATH OpenOpenAlexFDO

Authors Johannes T. N. Krebs

Publication date 23 January 2018

Published in Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1701.05380

zbMATH Keywords

functional data analysistime seriesnonparametric statistics\(\beta\)-mixinglarge deviation inequalityasymptotic inequalities

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Large deviations (60F10) Nonparametric statistical resampling methods (62G09)

Abstract: We give a new large deviation inequality for sums of random variables of the form $Z_k=f(X_k,X_t)$ for $k,tinmathbbN$, $t$ fixed, where the underlying process $X$ is $$-mixing. The inequality can be used to derive concentration inequalities. We demonstrate its usefulness in the functional kernel regression model of Ferraty et al. (2007) where we study the consistency of dynamic forecasts.

Recommendations

• On the asymptotic normality of kernel estimators of the long run covariance of functional time series
• scientific article; zbMATH DE number 6961998
• scientific article; zbMATH DE number 7266447
• Extreme quantile estimation for \(\beta\)-mixing time series and applications
• Nonparametric kernel regression estimation for functional stationary ergodic data: Asymptotic properties
• scientific article; zbMATH DE number 1865880
• Estimation of the asymptotic variance of kernel density estimators for continuous time processes
• A multidimensional functional central limit theorem for an empirical estimator of a continuous-time semi-Markov kernel

Cites work

• scientific article; zbMATH DE number 3840941 (Why is no real title available?)
• A Bernstein-type inequality for \(U\)-statistics and \(U\)-processes
• A CENTRAL LIMIT THEOREM AND A STRONG MIXING CONDITION
• A distribution-free theory of nonparametric regression
• Advances on asymptotic normality in non-parametric functional time series analysis
• Basic properties of strong mixing conditions. A survey and some open questions
• Bernstein inequality and moderate deviations under strong mixing conditions
• Convergence of Distributions Generated by Stationary Stochastic Processes
• Coupling for \(\tau\)-dependent sequences and applications
• Large deviations and strong mixing
• Mixing: Properties and examples
• NONPARAMETRIC REGRESSION ON FUNCTIONAL DATA: INFERENCE AND PRACTICAL ASPECTS
• On Strong Mixing Conditions for Stationary Gaussian Processes
• On the validity of the bootstrap in non-parametric functional regression
• Probability Inequalities for Sums of Bounded Random Variables
• Probability inequalities for bounded random vectors
• Propri�t�s de convergence presque compl�te du pr�dicteur � noyau
• Some Limit Theorems for Stationary Processes

Cited in

(2)

• Non-parametric regression for spatially dependent data with wavelets
• Concentration inequalities for kernel density estimators under uniform mixing

This page was built for publication: A large deviation inequality for \(\beta\)-mixing time series and its applications to the functional kernel regression model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q680473)