English

Stick-breaking processes with exchangeable length variables

Statistics Theory 2021-07-20 v2 Probability Methodology Other Statistics Statistics Theory

Abstract

Our object of study is the general class of stick-breaking processes with exchangeable length variables. These generalize well-known Bayesian non-parametric priors in an unexplored direction. We give conditions to assure the respective species sampling process is proper and the corresponding prior has full support. For a rich sub-class we explain how, by tuning a single [0,1][0,1]-valued parameter, the stochastic ordering of the weights can be modulated, and Dirichlet and Geometric priors can be recovered. A general formula for the distribution of the latent allocation variables is derived and an MCMC algorithm is proposed for density estimation purposes.

Keywords

Cite

@article{arxiv.2008.04475,
  title  = {Stick-breaking processes with exchangeable length variables},
  author = {María F. Gil-Leyva and Ramsés H. Mena},
  journal= {arXiv preprint arXiv:2008.04475},
  year   = {2021}
}

Comments

Accepted for publication by the Journal of the American Statistical Association. 44 pages, 11 figures, supplementary material

R2 v1 2026-06-23T17:46:03.278Z