Title: Estimation for univariate and bivariate reinforced urn processes under left-truncation and right-censoring
Authors: Luis Antonio Souto Arias - Centrum Wiskunde and Informatica-Delft University of Technology (Netherlands) [presenting]
Pasquale Cirillo - University of Nicosia (Cyprus)
Cornelis W Oosterlee - Centrum Wiskunde and Informatica-Delft University of Technology (Netherlands)
Abstract: Reinforced Urn Processes (RUPs) represent a flexible class of Bayesian nonparametric models suitable for dealing with possibly right-censored and left-truncated observations. A reliable estimation of their hyper-parameters is, however, missing in the literature. We, therefore, propose an extension of the Expectation-Maximization (EM) algorithm for RUPs, both in the univariate and the bivariate case. Furthermore, a new methodology combining EM and the prior elicitation mechanism of RUPs is developed: the Expectation-Reinforcement algorithm. Using a well-known Canadian dataset, the performances of both algorithms are studied in the context of joint and last survivor annuity pricing.