On the Generation of Pseudo-Random Stable Paretian Variates

Stefan Mittnik
University of Kiel, Germany
Mittnik@stat-econ.Uni-Kiel.de

Toker Doganoglu
State University of New York, Stony Brook

Abstract

Stable Paretian distributions have become increasingly important in financial modeling. The lack of a general analytic expression for the density or distribution function represents a serious difficulty in practical implementations. One consequence is the lack of reliable random number generators for the stable Paretian distribution, especially for the asymmetric case. In this paper we present an algorithm for generating stable Paretian random numbers and compare it with the widely used algorithm of Chambers et al. (1976).