The Dirichlet process has a roughly size ordered representation in terms of beta random variables, called a stick-breaking representation (Sethuraman, 1994). Similar results hold for the beta process, the Hierarchical Dirichlet process (Teh et al., 2006) and the Pitman-Yor process (Ishwaran and James, 2001). Is there a necessary and sufficient condition for the existence of stick breaking representations for various random measures?

  • $\begingroup$ How do you define a stick breaking representation? Is it just what you get from combining a countable sample taking independently from some distribution and combining it with a distribution on $\mathbb{N}$? $\endgroup$ – Michael Greinecker Mar 17 '18 at 19:02
  • $\begingroup$ I don't think there's a rigorous definition of stick-breaking, but that's what I'm looking for, yes. $\endgroup$ – Shannon S. Mar 18 '18 at 16:24

Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.