Noticimat: 22

Resumen: Abstract. In binary regression, symmetric links such as logit and probit are usually considered as standard. However, in the presence of unbalancing of ones and zeros, these links can be inappropriate and inflexible to fit the skewness in the response curve and likely to lead to misspecification. This is the case of covering some type of insurance, where it can be observed that the probability of a given binary response variable approaches zero at different rates than it approaches one. Furthermore, when usual links are considered, there is not a skewness parameter associated with the distribution chosen that, regardless of the linear predictor, is easily interpreted. In order to overcome such problems, a proposal for the construction of a set of new skew links is developed in this paper, where some of their properties are discussed. In this context, power links and their reversal versions are presented. A Bayesian inference approach using MCMC is developed for the presented models. The methodology is illustrated considering a sample of  motor insurance policyholders selected randomly by gender. Results suggest that the proposed link functions are more appropriate than other alternative link functions commonly used in the literature.

Resumen: In this work we introduce a spatio-temporal process starting with a specific case that allows for Pareto marginal distributions. Dependence in space and time is introduced through the use of latent variables in a hierarchical fashion. We review the construction of the process and study some of its properties. Instead of composite likelihood approaches, we follow a Bayesian approach to estimate the model and show how to obtain posterior inference via MCMC methods. The performance of the process is illustrated with simulations and a pollution dataset of monthly maxima ozone concentration and compared to other alternative models. We also consider generalizations of this model that allow for other marginal distributions and other representations at the latent level.

Del 14 al 16 de junio se realizará en el Centro Universitario de Ciencias Exactas e Ingenierías (CUCEI) de la Universidad de Guadalajara el VII Congreso Internacional de Métodos Numéricos en Ingeniería, que tiene por objetivo recopilar los trabajos recientes más relevantes en investigación y aplicación práctica relacionados con algún aspecto de los métodos numéricos en ingeniería y en ciencias aplicadas.

Del 15 al 19 de junio se realizará en este Centro el VII International Workshop on Perspectives on High-dimensional Data Analysis, cuyo propósito es fomentar la investigación en el área de análisis de datos de alta dimensionalidad.

Del 27 de mayo al 5 de junio el Dr. Óscar Dalmau Cedeño visitó la Universidad de Groningen, Holanda, para colaborar con el Dr. Nikolai Petkrov en el Instituto Johann Bernoulli for Mathematics and Computer Science y participar en el Coloquio de ciencias de la computación de esa universidad.

Luis Daniel Bravo Ramírez, quien el pasado lunes 5 se graduó del programa de Licenciatura en Computación con la presentación y defensa de su tesis Algoritmo distribuido de explotación para ambientes desconocidos con múltiples obstáculos y múltiples agentes, dirigida por el Dr. Rafael Eric Murrieta Cid (CIMAT). El jurado estuvo integrado por la Dra. Claudia Elvira Esteves Jaramillo (UG), presidenta; el Dr. Jean Bernard Hayet (CIMAT), secretario; y el Dr. Héctor Manuel Becerra Fermín (CIMAT), vocal.

Actividades de divulgación