Author(s)

Jorge A. Achcar, Sílvia R. C. Lopes, Josmar Mazucheli, Raquel R. Linhares

Departament of Statistics, UEM, Maringá, Brazil.
Mathematical Institute, UFRGS, Porto Alegre, Brazil.
Medical School, USP, Ribeir?o Preto, Brazil.

In this work, we study some computational aspects for the Bayesian analysis involving stable distributions. It is well known that, in general, there is no closed form for the probability density function of stable distributions. However, the use of a latent or auxiliary random variable facilitates to obtain any posterior distribution when being related to stable distributions. To show the usefulness of the computational aspects, the methodology is applied to two examples: one is related to daily price returns of Abbey National shares, considered in [1], and the other is the length distribution analysis of coding and non-coding regions in a Homo sapiens chromosome DNA sequence, considered in [2]. Posterior summaries of interest are obtained using the OpenBUGS software.

Stable Laws; Bayesian Analysis; DNA Sequences; MCMC Methods; OpenBUGS Software

J. Achcar, S. Lopes, J. Mazucheli and R. Linhares, "A Bayesian Approach for Stable Distributions: Some Computational Aspects," Open Journal of Statistics, Vol. 3 No. 4, 2013, pp. 268-277. doi: 10.4236/ojs.2013.34031.