Discrete approximation of a mixture distribution via restricted divergence

Abstract

Mixture distributions arise in many application areas, for example as marginal distributions or convolutions of distributions. We present a method of constructing an easily tractable discrete mixture distribution as an approximation to a mixture distribution with a large to infinite number, discrete or continuous, of components. The proposed DIRECT (Divergence Restricting Conditional Tesselation) algorithm is set up such that a pre-specified precision, defined in terms of Kullback-Leibler divergence between true distribution and approximation, is guaranteed. Application of the algorithm is demonstrated in two examples.

16 pages, 4 figures

References in corpus (2)

• Bayesian random-effects meta-analysis using the bayesmeta R package
• Meta-analysis of few small studies in orphan diseases

Cited by in corpus (8)

• Bayesian random-effects meta-analysis using the bayesmeta R package
• On weakly informative prior distributions for the heterogeneity parameter in Bayesian random-effects meta-analysis
• Using the bayesmeta R package for Bayesian random-effects meta-regression
• Recent advances in methodology for clinical trials in small populations: the InSPiRe project
• Testing Gravity with Gravitational Waves from Binary Black Hole Mergers: Contributions from Amplitude Corrections
• Model averaging for robust extrapolation in evidence synthesis
• Projection predictive variable selection for discrete response families with finite support
• Factorizable joint shift revisited