Statistical model generates random numbers using beta-binomial and dirichlet-multinomial distributions, implying precise simulations of mixing states.
A statistical model for describing mixing states of a binary mixture was proposed by Yoshizawa and Shindo [1]. This model, based on a beta-binomial distribution, enables one to describe various variations of characteristics in space and time scales. In this paper, an algorithm for generating beta-binomially distributed random numbers is presented on the basis of the Polya urn scheme. Focusing on the ratio changes enables one to successfully eliminate an overflow problem which occurs in the scheme. Although the algorithm is not perfectly efficient, it is precise and easily understandable. An algorithm for the n-ary case, Dirichlet-multinomially distributed random number generation, is also presented as a natural extension of the binary case.
No takes yet. Share an insight, caveat, or question.
Quarshie et al. (1992) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: