Means of a Dirichlet process and multiple hypergeometric functions.
From MaRDI portal
Abstract: The Lauricella theory of multiple hypergeometric functions is used to shed some light on certain distributional properties of the mean of a Dirichlet process. This approach leads to several results, which are illustrated here. Among these are a new and more direct procedure for determining the exact form of the distribution of the mean, a correspondence between the distribution of the mean and the parameter of a Dirichlet process, a characterization of the family of Cauchy distributions as the set of the fixed points of this correspondence, and an extension of the Markov-Krein identity. Moreover, an expression of the characteristic function of the mean of a Dirichlet process is obtained by resorting to an integral representation of a confluent form of the fourth Lauricella function. This expression is then employed to prove that the distribution of the mean of a Dirichlet process is symmetric if and only if the parameter of the process is symmetric, and to provide a new expression of the moment generating function of the variance of a Dirichlet process.
Distributions of random means of measure-valued gamma amd Dirichlet processes are described. Given a finite measure \(\alpha\) on \textbf{R}, a measure-valued random element \(\gamma\) is called a gamma process with the parameter \(\alpha\) if for any collection of sets \(B_1\),\dots,\(B_k\) the random variables \(\gamma(B_1)\),\dots,\(\gamma(B_k)\) are independent and gamma-distributed with \(\mathbf E\gamma(B_i)=\text{Var}(\gamma(B_i))=\alpha(B_i)\). Analogousely \(\varphi\) is a Dirichlet process with the parameter \(\alpha\) if \((\varphi(B_1),\dots,\varphi(B_k))\) has a Dirichlet distribution with parameter \((\alpha(B_1),\dots,\alpha(B_k))\). Different characterizations of random means \(\varphi(I)=\int x\varphi(dx)\) and \(\gamma(I)=\int x\gamma(dx)\) are given. Lévy-Khinchin representation for the characteristic function of \(\varphi(I)\) is derived. It is shown that any finite \(\alpha\) with \(\int \log(1+|x|)\alpha(dx)\) is determined by the distribution of \(\varphi(I)\). The distribution of \(\varphi(I)\) is symmetric iff \(\alpha\) is symmetric. Exact forms of PDF of \(\varphi(I)\) are derived for \(\alpha\) being Cauchy, uniform or Gaussian distribution. These results are based on the extension of Markov-Krein identity and integral representation of a confluent form of the fourth Lauricella function.
Recommendations
- Characteristic functions of means of distributions chosen from a Dirichlet process
- Theory and numerical analysis for exact distributions of functionals of a Dirichlet process
- Moment-based approximations for the law of functionals of Dirichlet processes
- Distribution functions of means of a Dirichlet process
- Exact inference for random Dirichlet means
Cites work
- A Bayesian analysis of some nonparametric problems
- Absolute continuity of infinitely divisible distributions
- An extension of the notion of a generalized Γ-convolution
- Bayesian Methods for Censored Categorical Data
- Characteristic functions of means of distributions chosen from a Dirichlet process
- Considerazioni generali sull’impostazione bayesiana di problemi non parametrici
- Considerazioni generali sull’impostazione Bayesiana di problemi non parametrici. Le medie associative nel contesto del processo aleatorio di Dirichlet parte II
- De Finetti's contribution to probability and statistics
- Distribution functions of means of a Dirichlet process
- Generalized gamma convolutions and related classes of distributions and densities
- scientific article; zbMATH DE number 3141417 (Why is no real title available?)
- scientific article; zbMATH DE number 48232 (Why is no real title available?)
- scientific article; zbMATH DE number 3489473 (Why is no real title available?)
- scientific article; zbMATH DE number 3527042 (Why is no real title available?)
- scientific article; zbMATH DE number 3611701 (Why is no real title available?)
- scientific article; zbMATH DE number 3630024 (Why is no real title available?)
- scientific article; zbMATH DE number 1126911 (Why is no real title available?)
- scientific article; zbMATH DE number 1560292 (Why is no real title available?)
- scientific article; zbMATH DE number 964178 (Why is no real title available?)
- scientific article; zbMATH DE number 3191506 (Why is no real title available?)
- scientific article; zbMATH DE number 3029912 (Why is no real title available?)
- Linear functionals and Markov chains associated with Dirichlet processes
- Multiple Hypergeometric Functions: Probabilistic Interpretations and Statistical Uses
- On the infinite divisbility of the Pareto distribution
- On the infinite divisibility of the lognormal distribution
- On the Markov-Krein identity and quasi-invariance of the gamma process
- On topological support of Dirichlet prior
- Proof of a conjecture of L. Bondesson concerning infinite divisibility of powers of a gamma variable
- Some new results for Dirichlet priors.
- The Markov-Krein correspondence in several dimensions
- Theory and numerical analysis for exact distributions of functionals of a Dirichlet process
- Three Multidimensional-integral Identities with Bayesian Applications
Cited in
(36)- Veneziano amplitudes, spin chains and abelian reduction of QCD
- Moments of Dirichlet splines and their applications to hypergeometric functions
- On the Markov-Krein identity and quasi-invariance of the gamma process
- Distribution of the main value for certain random measures
- A Bayesian semiparametric vector multiplicative error model
- Gamma-Dirichlet algebra and applications
- On a generalized Chu-Vandermonde identity
- Characteristic functionals of Dirichlet measures
- Normalized random measures driven by increasing additive processes
- Functionals of Dirichlet processes, the Cifarelli-Regazzini identity and beta-gamma processes
- Distributions of linear functionals of two parameter Poisson-Dirichlet random measures
- A new multivariate transform and the distribution of a random functional of a Ferguson-Dirichlet process
- A stochastic equation for the law of the random Dirichlet variance
- Exact inference for random Dirichlet means
- Bayesian nonparametric analysis for a generalized Dirichlet process prior
- Laplace approximation of Lauricella functions \(F_A\) and \(F_D\)
- An integration by parts formula for functionals of the Dirichlet-ferguson measure, and applications
- On a class of random probability measures with general predictive structure
- A Monotone Approximation to the Wasserstein Diffusion
- On the distribution of certain functionals of two distinguished random probabilities
- Multiple Hypergeometric Functions: Probabilistic Interpretations and Statistical Uses
- Lauricella and Humbert functions through probabilistic tools
- Asymptotic power of sphericity tests for high-dimensional data
- On a rapid simulation of the Dirichlet process
- Dirichlet mean identities and laws of a class of subordinators
- A revisit of the distribution of linear combinations of Dirichlet components
- The Lauricella hypergeometric function \(F_D^{(N)}\), the Riemann-Hilbert problem, and some applications
- Goodness-of-fit tests based on the distance between the Dirichlet process and its base measure
- On the posterior distribution of classes of random means
- The two-parameter Poisson-Dirichlet point process
- Specification of the Base Measure of Nonparametric Priors via Random Means
- Quantitative multidimensional central limit theorems for means of the Dirichlet-Ferguson measure
- Random probability measures with fixed mean distributions
- Enriched Pitman-Yor processes
- Characteristic functions of means of distributions chosen from a Dirichlet process
- Distributional properties of means of random probability measures
This page was built for publication: Means of a Dirichlet process and multiple hypergeometric functions.
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1879833)
