Negative Binomial Construction of Random Discrete Distributions on the Infinite Simplex

From MaRDI portal



Abstract: The Poisson-Kingman distributions, mathrmPK(ho), on the infinite simplex, can be constructed from a Poisson point process having intensity density ho or by taking the ranked jumps up till a specified time of a subordinator with L'evy density ho, as proportions of the subordinator. As a natural extension, we replace the Poisson point process with a negative binomial point process having parameter r>0 and L'evy density ho, thereby defining a new class mathrmPK(r)(ho) of distributions on the infinite simplex. The new class contains the two-parameter generalisation mathrmPD(alpha,heta) of Pitman and Yor (1997) when heta>0. It also contains a class of distributions derived from the trimmed stable subordinator. We derive properties of the new distributions, with particular reference to the two most well-known mathrmPK distributions: the Poisson-Dirichlet distribution mathrmPK(hoheta) generated by a Gamma process with L'evy density hoheta(x)=hetae−x/x, x>0, heta>0, and the random discrete distribution, mathrmPD(alpha,0), derived from an alpha-stable subordinator.












This page was built for publication: Negative Binomial Construction of Random Discrete Distributions on the Infinite Simplex

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4559029)