Título: Regression models for time varying extremes
Palestrante: Fernando Ferraz do Nascimento – Departamento de Estatística – UFPI
Data: 30 de Novembro de 2015 (Segunda-feira)
Horário: 15:00 horas
Local: Auditório do CCET – UFRN
* Depois da apresentação é oferecido um coffee-break para socialização e discussões científicas.
Abstract: A common approach to modeling extreme data is to consider the distribution of the exceedance value over a high threshold. This approach is based on the distribution of excess, which follows the generalized Pareto distribution (GPD) and has proven to be adequate for this type of situation. As with all data involving analysis in time, excesses above a threshold may also vary and suffer from the influence of covariates. Thus, the GPD distribution can be modeled by entering the presence of these factors. This paper presents a new model for extreme values, where GPD parameters are written on the basis of a dynamic regression model. The estimation of the model parameters is made under the Bayesian paradigm, with sampling points via MCMC. As with environmental data, behavior data is related to other factors such as time and covariates like latitude, distance from the sea, etc. Simulation studies have shown the efficiency and identifiability of the model, and applying real rain data from the state of Piaui, Brazil, shows the advantage in predicting and interpreting the model against other similar models proposed in the literature.
Mais informações no site do PPgMAE: https://sigaa.ufrn.br/sigaa/public/programa/noticias_desc.jsf?lc=pt_BR&id=2595¬icia=115468244