M. González Velasco, C. Minuesa Abril, I. M. del Puerto García
Branching processes are one of the most remarkable models for the description of the dynamic of populations. Within the class of these processes, this work is focused on the controlled branching process, a generalization of the classical model that incorporates a random control function which determines the number of progenitors in each generation.
The aim of this work is to develop a procedure which provides, for the main parameters of the model, robust estimators against outliers in a Bayesian outlook. Owing to robust procedures against outliers have been scarcely studied in this field and no result has been obtained in a Bayesian context, this work presents pioneer results. For our purpose, we consider the sample given by the entire family tree and we make use of disparity measures. Asymptotic properties and robustness measures of these estimators are studied. Finally, the accuracy of the method is illustrated by the way of simulated examples developed with R.
Palabras clave: Branching process, Controlled process, Disparity measure, Robustness.Programado
L05.4 Procesos Estocásticos I
5 de septiembre de 2016 11:30