Decompounding discrete distributions: A non-parametric Bayesian approach

Abstract

Suppose that a compound Poisson process is observed discretely in time and assume that its jump distribution is supported on the set of natural numbers. In this paper we propose a non-parametric Bayesian approach to estimate the intensity of the underlying Poisson process and the distribution of the jumps. We provide a MCMC scheme for obtaining samples from the posterior. We apply our method on both simulated and real data examples, and compare its performance with the frequentist plug-in estimator proposed by Buchmann and Grübel. On a theoretical side, we study the posterior from the frequentist point of view and prove that as the sample size $n\to \infty$, it contracts around the `true', data-generating parameters at rate $1/\sqrt{n}$, up to a $\log n$ factor.

27 pages, 7 figures

References in corpus (7)

• Posterior convergence rates of Dirichlet mixtures at smooth densities
• Contributed Discussion to Uncertainty Quantification for the Horseshoe by Stéphanie van der Pas, Botond Szabó and Aad van der Vaart
• Estimation for Lévy processes from high frequency data within a long time interval
• Bernstein -- von Mises theorems for statistical inverse problems II: Compound Poisson processes
• Efficient nonparametric inference for discretely observed compound Poisson processes
• Nonparametric Bayesian inference for multidimensional compound Poisson processes
• Nonparametric Bayesian inference for Gamma-type Lévy subordinators

Cited by in corpus (1)

• Nonparametric Bayesian volatility estimation for gamma-driven stochastic differential equations