A non-parametric Bayesian approach to decompounding from high frequency data

DOI10.1007/S11203-016-9153-1MaRDI QIDQ1744221zbMATH OpenOpenAlexWikidataFDO

Authors Shota Gugushvili, Peter Spreij, Frank van der Meulen

Publication date 16 April 2018

Published in Statistical Inference for Stochastic Processes (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1507.03263

zbMATH Keywords

nonparametric Bayesian estimationposterior contraction ratecompound Poisson processhigh frequency observations

Mathematics Subject Classification ID

Bayesian inference (62F15) Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20)

Abstract: Given a sample from a discretely observed compound Poisson process, we consider non-parametric estimation of the density $f_0$ of its jump sizes, as well as of its intensity $lambd{a}_0.$ We take a Bayesian approach to the problem and specify the prior on $f_0$ as the Dirichlet location mixture of normal densities. An independent prior for $lambd{a}_0$ is assumed to be compactly supported and to possess a positive density with respect to the Lebesgue measure. We show that under suitable assumptions the posterior contracts around the pair $(lambd{a}_0,f_0)$ at essentially (up to a logarithmic factor) the $sqrtnDelta$-rate, where $n$ is the number of observations and $Delta$ is the mesh size at which the process is sampled. The emphasis is on high frequency data, $Deltao0$, but the obtained results are also valid for fixed $Delta$. In either case we assume that $nDeltaightarrowinfty$. Our main result implies existence of Bayesian point estimates converging (in the frequentist sense, in probability) to $(lambd{a}_0,f_0)$ at the same rate. We also discuss a practical implementation of our approach. The computational problem is dealt with by inclusion of auxiliary variables and we develop a Markov Chain Monte Carlo algorithm that samples from the joint distribution of the unknown parameters in the mixture density and the introduced auxiliary variables. Numerical examples illustrate the feasibility of this approach.

Recommendations

• Decompounding discrete distributions: A nonparametric Bayesian approach
• Nonparametric Bayesian inference for multidimensional compound Poisson processes
• Density estimation for compound Poisson processes from discrete data
• Efficient nonparametric inference for discretely observed compound Poisson processes
• Nonparametric estimation for compound Poisson process via variational analysis on measures

Cites work

• scientific article; zbMATH DE number 5770656 (Why is no real title available?)
• scientific article; zbMATH DE number 3911491 (Why is no real title available?)
• scientific article; zbMATH DE number 3780407 (Why is no real title available?)
• scientific article; zbMATH DE number 597901 (Why is no real title available?)
• scientific article; zbMATH DE number 1026574 (Why is no real title available?)
• scientific article; zbMATH DE number 1085980 (Why is no real title available?)
• scientific article; zbMATH DE number 1102528 (Why is no real title available?)
• scientific article; zbMATH DE number 1834045 (Why is no real title available?)
• A Bayesian analysis of some nonparametric problems
• A Donsker theorem for Lévy measures
• A general framework for the parametrization of hierarchical models
• A kernel type nonparametric density estimator for decompounding
• Adaptive Estimation for Lévy Processes
• An oracle inequality for penalised projection estimation of Lévy densities from high-frequency observations
• Asymptotic methods in statistical decision theory
• Bayesian analysis of stochastic process models
• Convergence rates of posterior distributions.
• Decompounding Poisson random sums: recursively truncated estimates in the discrete case
• Decompounding: an estimation problem for Poisson random sums.
• Density estimation for compound Poisson processes from discrete data
• Entropies and rates of convergence for maximum likelihood and Bayes estimation for mixtures of normal densities.
• Estimation for Lévy processes from high frequency data within a long time interval
• Exact mean integrated squared error
• Finite mixture models
• Handbook of Markov Chain Monte Carlo
• High-frequency Donsker theorems for Lévy measures
• Lévy matters IV. Estimation for discretely observed Lévy processes
• Nonparametric Bayesian inference for multidimensional compound Poisson processes
• Nonparametric adaptive estimation for pure jump Lévy processes
• Nonparametric density estimation in compound Poisson processes using convolution power estimators
• Nonparametric estimation for Lévy models based on discrete-sampling
• On a class of Bayesian nonparametric estimates: I. Density estimates
• Posterior consistency of Dirichlet mixtures for estimating a transition density
• Posterior convergence rates of Dirichlet mixtures at smooth densities
• Small-time moment asymptotics for Lévy processes
• The Calculation of Posterior Distributions by Data Augmentation

Cited in

(9)

• An inverse problem for infinitely divisible moving average random fields
• Nonparametric statistical inference for compound models
• Nonparametric Bayesian inference for multidimensional compound Poisson processes
• Bernstein-von Mises theorems for statistical inverse problems. II: Compound Poisson processes
• Nonparametric Bayesian volatility estimation for gamma-driven stochastic differential equations
• Efficient nonparametric inference for discretely observed compound Poisson processes
• Bayesian Inference via Filtering Equations for Ultrahigh Frequency Data (I): Model and Estimation
• Bayesian Inference via Filtering Equations for Ultrahigh Frequency Data (II): Model Selection
• Approximate Bayesian computations to fit and compare insurance loss models

This page was built for publication: A non-parametric Bayesian approach to decompounding from high frequency data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1744221)