Time varying extreme pattern with dynamic models - Dani Gamerman, IM/UFRJ

Resumo: This talk is concerned with the analysis of time series data with temporal dependence through extreme events. This is achieved via a model formulation that considers separately the central part and the tail of the distributions, using a two component mixture model. Extremes beyond a threshold are assumed to follow a generalized Pareto distribution (GPD). Temporal dependence is induced by allowing to GPD parameter to vary with time. Temporal variation and dependence is introduced at a latent level via the novel use of dynamic linear models (DLM). Novelty lies in the time variation of the shape of the resulting distribution. These changes in limiting regimes as time changes reflect better the data behaviour, with important gains in estimation and interpretation. The central part follows a nonparametric, mixture approach. The uncertainty about the threshold is explicitly considered. Posterior inference is performed through Markov Chain Monte Carlo (MCMC) methods. A variety of scenarios can be entertained and include the possibility of alternation of presence and absence of a finite upper limit of the distribution for different time periods. Simulations are carried out in order to analyze the performance of our proposed model. We also apply the proposed model to financial time series: returns of Petrobras stocks and Bovespa index. Results show advantage of our proposal over currently entertained models such as stochastic volatility, with improved estimation of high quantiles and extremes. Joint work with Fernando Nascimento and Hedibert Lopes.

Local: Auditório do IME e no link a seguir

https://www.youtube.com/channel/UCC96Rmc3qKEYkKk187IcLdA/live

Link da palestra: 

https://www.youtube.com/watch?v=KzzXo8DPfkQ&t=110s

Minicurrículo: O Prof. Dani Gamerman é graduado em Engenharia Mecânica pelo IME em 1980, Mestre em Estatística pelo IMPA em 1983 e Doutor em Estatística pela Universidade de Warwick em 1987. Professor Titular da UFRJ desde 1996, Bolsista de pesquisa do CNPq desde 1987. Autor dos livros Monte Carlo Markov Chain: Stochastic Simulation for Bayesian Inference, publicado pela Chapman and Hall em 1997 (1a. edição) e em 2006 (2a. edição, com Hedibert F. Lopes) e Statistical Inference: an Integrated Approach (com Helio S. Migon), publicado pela Arnold em 1999, além de livros nacionais.  Atualmente tem suas atividades de pesquisas em modelos dinâmicos, estatística espacial, análise de sobrevivência, teoria de extremos, TRI, simulação estocástica, econometria e inferência Bayesiana.

Palestrante: 
Professor Dani Gamerman
Universidade do Palestrante: 
IM/UFRJ
Data e Hora: 
sexta-feira, 2 Junho, 2017 -
11:00 to 12:00