Conjugacy as a Distinctive Feature of the Dirichlet Process

78 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Bayesian inference with dependent normalized completely random measures (2014, methodology): “Such a procedure has then been extended and analyzed for general univariate CRMs in [18,19,36].”
Bayesian Nonparametric Analysis for a Generalized Dirichlet Process Prior (2005, methodology): “From Proposition 1 in James et al. (2004), variance, covariance and skewness of a normalized RMI based upon a subordinator are given by (6), (8) and (9), respectively, with Ia,γ defined as Ia,γ =a ∫ +∞ 0 u e−a ψ(u) ∫ +∞ 0 v2 e−uv ν(dv)du, where ψ stands for the Laplace exponent of the random…”
Posterior Analysis for Normalized Random Measures with Independent Increments (2009, background): “This represents a challenging issue since, with the exception of the Dirichlet process, NRMIs are not conjugate as shown in James et al. (2006).”
On the stick-breaking representation of normalized inverse Gaussian priors (2012, methodology): “Moreover, from [26] it is immediate to deduce that the normalized inverse Gaussian process, and more generally any homogeneous normalized random measure with independent increments [30, 14], is invariant under size biased permutations.”