Statistical Inference for a New Class of Multivariate Pareto Distributions

Solutions to the parameter estimation problem of the multivariate Pareto distribution of Asimit et al. (2010) are developed and exemplified numerically. Namely, a density of the aforementioned multivariate Pareto distribution with respect to a dominating measure, rather than the corresponding Lebesgue measure, is specified and then employed to investigate the maximum likelihood estimation (MLE) approach. Also, an adapted variant of the expectation maximization (EM) algorithm is investigated. The method of moments is discussed as a convenient way to obtain starting values for the numerical optimization procedures associated with the MLE and EM methods