Finite mixture of alpha-stable distributions

6 Over the last decades, the α-stable distribution has proved to be a very efficient 7 model for impulsive data. In this paper, we propose an extension of stable distribu8 tions, namely mixture of α-stable distributions to model multimodal, skewed and 9 impulsive data. A fully Bayesian framework is presented for the estimation of the 10 stable density parameters and the mixture parameters. As opposed to most previ11 ous work on mixture models, the model order is assumed unknown and is estimated 12 using reversible jump Markov chain Monte Carlo. It is important to note that the 13 Gaussian mixture model is a special case of the presented model, which also provides 14 additional flexibility to model skewed and impulsive phenomena. The algorithm is 15 tested using synthetic and real data, accurately estimating α-stable parameters, 16 mixture coefficients and the number of components in the mixture. 17