Publicação

Parameter estimation and dependence characterization of the MAR(1) process

Ver documento

Detalhes bibliográficos
Resumo:Classical linear ARMA with normal distributed noises are not suitable for heavy tailed phenomena. MARMA processes obtained by replacing summation by the maximum operator are more appropriate. We consider unit Fréchet first order MARMA, denoted MAR(1), and present a characterization based on ordinal autocorrelation. An estimator of the model's parameter and respective consistency and asymptotic normality properties are also stated.
Autores principais:Ferreira, Marta Susana
Assunto:Autoregressive processes Heavy tail Estimation of parameters Ordinal autocorrelation
Ano:2012
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso aberto
Instituição associada:Universidade do Minho
Idioma:inglês
Origem:RepositóriUM - Universidade do Minho
Descrição
Resumo:Classical linear ARMA with normal distributed noises are not suitable for heavy tailed phenomena. MARMA processes obtained by replacing summation by the maximum operator are more appropriate. We consider unit Fréchet first order MARMA, denoted MAR(1), and present a characterization based on ordinal autocorrelation. An estimator of the model's parameter and respective consistency and asymptotic normality properties are also stated.