99-08-23.ley

A Note on Transformed Density Rejection

Josef Leydold

Abstract

In this paper we describe a version of transformed density rejection that requires less uniform random numbers. Random variates below the squeeze are generated by inversion. For the expensive part between squeeze and density an algorithm that uses a coverering with triangles is introduced.

CR Categories and Subject Descriptors: G.3 [Probability and Statistics]: Random number generation

Mathematics Subject Classification: 65C10 (Random Number Generation); 65U05 (Numerical methods in probability and statistics), 11K45 (Pseudo-random numbers, Monte Carlo methods)

General Terms: Algorithms

Key Words: random number generation, non-uniform, transformed density rejection, log-concave, T-concave, universal method

Download Preprint

Josef.Leydold@statistik.wu-wien.ac.at