A multivariate counting process with Weibull-distributed first-arrival times. (Q1431816)

A special multivariate counting process is constructed. Its univariate components are doubly stochastic non-homogeneous Poisson point processes (sometimes also called Cox processes) with power intensity functions that are proportional to each other. The structure of dependence between these processes is given by the Gumbel-Hougaard copula function, or equivalently, by stochastic mixing with respect to the probability distribution with a positive stable density. The corresponding simulation issues are touched upon. Three possible applications to model a cognitive process in psychology are considered: a horse race model with several dependent channels, a dependent parallel-counter model and an interactive coactivation model.