Faculdade

Investigação

Bootstrap methods for dependent data. Application to extremal index estimation

TítuloBootstrap methods for dependent data. Application to extremal index estimation
Publication TypeUnpublished
Year of Publication2005
AuthorsGomes PD, Neves MM, Mexia JT
Series TitlePreprint
AbstractThe main objective of statistics of extremes is the estimation of parameters of rare events. The introduction of a new parameter, the extremal index enables a straightforward extension of the classic results for the independent case to stationary processes. Extremal index estimators proposed in the literature are strongly dependent on the high level un. Our objective is to use and to compare block bootstrap procedures to estimate the extremal index.
URLhttp://www.dm.fct.unl.pt/sites/www.dm.fct.unl.pt/files/preprints/2005/9_05.pdf