Half-region depth for stochastic processes

DOI10.1016/J.JMVA.2015.07.012zbMATH Open1339.60032arXiv1401.5817OpenAlexW1650514918MaRDI QIDQ893170FDOQ893170

Authors: Jim Kuelbs, Joel Zinn 

Publication date: 13 November 2015

Published in: Journal of Multivariate Analysis (Search for Journal in Brave)

Abstract: We study the concept of half-region depth, introduced by Lopez-Pintado and Romo in 2011. We show that for a wide variety of standard stochastic processes, such as Brownian motion and other symmetric stable processes with stationary independent increments tied down at 0, half-region depth assigns depth zero to all sample functions. To alleviate this difficulty we introduce a method of smoothing, which often not only eliminates the problem of zero depth, but allows us to extend the theoretical results on consistency in that paper up to the $sqrtn$ level for many smoothed processes.

Full work available at URL: https://arxiv.org/abs/1401.5817

Recommendations

• Limit theorems for quantile and depth regions for stochastic processes
• A half-region depth for functional data
• Depth-Bounded Approximations of Probability
• Local half-region depth for functional data
• Empirical depth processes
• Computing halfspace depth and regression depth
• Dirichlet depths for point process
• Multivariate functional halfspace depth
• Estimating the probability that a multidimensional random process reaches the boundary of a region
• Uniform convergence rates for halfspace depth

zbMATH Keywords

consistencyBrownian motionempirical processescentral limit theoremssymmetric stable processeshalf-region depth

Mathematics Subject Classification ID

Asymptotic distribution theory in statistics (62E20) Central limit and other weak theorems (60F05) Brownian motion (60J65) Functional limit theorems; invariance principles (60F17) Stable stochastic processes (60G52) General theory of stochastic processes (60G07)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Title not available (Why is that?)
• A half-region depth for functional data
• The random Tukey depth
• Uniform Central Limit Theorems
• Some intriguing properties of Tukey's half-space depth
• On data depth in infinite dimensional spaces
• Integrability of Infinite Sums of Independent Vector-Valued Random Variables
• Sums of independent Banach space valued random variables
• A central limit theorem under metric entropy with \(L_ 2\) bracketing
• Empirical Quantile CLTs for Time-dependent Data
• Concerns with functional depth
• A CLT for empirical processes involving time-dependent data
• Some Exponential Moments of Sums of Independent Random Variables
• Half-region depth for stochastic processes

Cited In (8)

• On a general definition of depth for functional data
• Limit Theorems for Quantile and Depth Regions for Stochastic Processes
• Halfspace depth does not characterize probability distributions
• Depth and outliers for samples of sets and random sets distributions
• Half-region depth for stochastic processes
• The deepest point for distributions in infinite dimensional spaces
• Model-based statistical depth with applications to functional data
• Halfspace depth and regression depth characterize the empirical distribution

This page was built for publication: Half-region depth for stochastic processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q893170)