Global smoothness estimation of a Gaussian process from general sequence designs

DOI10.1214/14-EJS925zbMATH Open1298.62141arXiv1211.2763OpenAlexW2053778794MaRDI QIDQ405335FDOQ405335

Authors: Delphine Blanke, Céline Vial 

Publication date: 5 September 2014

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: We consider a real Gaussian process $X$ having a global unknown smoothness $$, $r_{scriptscriptstyle0}inmathds{N}_0$ and $$, with $X^{(r_{scriptscriptstyle0})}$ (the mean-square derivative of $X$ if $r_{scriptscriptstyle0}ge1$) supposed to be locally stationary with index $$. From the behavior of quadratic variations built on divided differences of $X$, we derive an estimator of $$ based on - not necessarily equally spaced - observations of $X$. Various numerical studies of these estimators exhibit their properties for finite sample size and different types of processes, and are also completed by two examples of application to real data.

Full work available at URL: https://arxiv.org/abs/1211.2763

Recommendations

• Estimation of number of the derivatives of a Gaussian process
• Assessing the number of mean square derivatives of a Gaussian process
• Estimating the order of mean-square derivatives with quadratic variations
• scientific article; zbMATH DE number 663682
• Semi-parametric estimation of the Hölder exponent of a stationary Gaussian process with minimax rates

zbMATH Keywords

divided differenceslocally stationary processinference for Gaussian processesquadratic variationsunevenly spaced data

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Markov processes: estimation; hidden Markov models (62M05) Gaussian processes (60G15) Non-Markovian processes: estimation (62M09) Numerical interpolation (65D05) Sample path properties (60G17)

Cites Work

• Designs for Regression Problems With Correlated Errors: Many Parameters
• Estimators of fractal dimension: assessing the roughness of time series and spatial data
• Quadratic variations and estimation of the local Hölder index of a Gaussian process
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Bound on Tail Probabilities for Quadratic Forms in Independent Random Variables
• Sampling designs for estimating integrals of stochastic processes
• Asymptotic optimality of regular sequence designs
• Average-case analysis of numerical problems
• Title not available (Why is that?)
• Title not available (Why is that?)
• Estimating the order of mean-square derivatives with quadratic variations
• Title not available (Why is that?)
• Designs for Regression Problems with Correlated Errors III
• Spline approximation of random processes and design problems
• Periodogram-based estimators of fractal properties
• Title not available (Why is that?)
• Large deviations in the piecewise linear approximation of Gaussian processes with stationary increments
• Wavelet coefficients of a Gaussian process and applications
• Sojourns and extremes of Gaussian processes
• Uniform reconstruction of Gaussian processes
• Spatial adaption for predicting random functions
• On the relationship between fractal dimension and fractal index for stationary stochastic processes
• Optimal designs for weighted approximation and integration of stochastic processes on \([0,\infty)\)
• Predicting integrals of stochastic processes
• Optimal designs for approximating the path of a stochastic process
• A note on the prediction error for small time lags into the future (Corresp.)
• Prediction of level crossings for normal processes containing deterministic components
• Approximating integrals of stochastic processes: extensions
• Title not available (Why is that?)
• ESTIMATION OF FRACTAL INDEX AND FRACTAL DIMENSION OF A GAUSSIAN PROCESS BY COUNTING THE NUMBER OF LEVEL CROSSINGS
• Estimating Functionals of a Stochastic Process
• Bayesian Wavelet Regression on Curves With Application to a Spectroscopic Calibration Problem
• Title not available (Why is that?)
• Assessing the number of mean square derivatives of a Gaussian process

Cited In (11)

• Asymptotic Analysis of Maximum Likelihood Estimation of Covariance Parameters for Gaussian Processes: An Introduction with Proofs
• Assessing the number of mean square derivatives of a Gaussian process
• Estimating jump intensity and detecting jump instants in the context of \(p\) derivatives
• Estimating the order of mean-square derivatives with quadratic variations
• Learning the smoothness of noisy curves with application to online curve estimation
• Estimation of number of the derivatives of a Gaussian process
• Efficient parametric estimation for a signal-plus-noise Gaussian model from discrete time observations
• Estimating the smoothness of a Gaussian random field from irregularly spaced data via higher-order quadratic variations
• On fixed-domain asymptotics, parameter estimation and isotropic Gaussian random fields with Matérn covariance functions
• Smoothness estimation of nonstationary Gaussian random fields from irregularly spaced data observed along a curve
• Detecting instants of jumps and estimating their intensity in the context of \(p\) derivatives with continuous or discrete data

Uses Software

• R

This page was built for publication: Global smoothness estimation of a Gaussian process from general sequence designs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q405335)