Ordered and size-biased frequencies in GEM and Gibbs models for species sampling
arXiv:1704.04732
Abstract
We describe the distribution of frequencies ordered by sample values in a random sample of size from the two parameter GEM random discrete distribution on the positive integers. These frequencies are a size-biased random permutation of the sample frequencies in either ranked order, or in the order of appearance of values in the sampling process. This generalizes a well known identity in distribution due to Donnelly and Tavaré (1986) for to the case . This description extends to sampling from Gibbs frequencies obtained by suitable conditioning of the GEM model, and yields a value-ordered version of the Chinese Restaurant construction of GEM and Gibbs frequencies in the more usual size-biased order of their appearance. The proofs are based on a general construction of a finite sample from any random frequencies in size-biased order from the associated exchangeable random partition of which they generate.
arXiv comment23 pages, some corrections to the first version
References in corpus (5)
- Poisson calculus for spatial neutral to the right processes
- Gibbs Partitions (EPPF's) Derived From a Stable Subordinator are Fox H and Meijer G Transforms
- Wright-Fisher construction of the two-parameter Poisson-Dirichlet diffusion
- Looking-backward probabilities for Gibbs-type exchangeable random partitions
- On a Gibbs characterization of normalized generalized Gamma processes