Efficient bootstrap simulation

Two basic sources of error are associated to the use of bootstrap methods: one is derived from the fact that the true distribution is substituted by a suitable estimate, and the other is simulation errors. Some techniques to reduce or quantify these errors are discussed in this work. Some of them su...

Descripción completa

Detalles Bibliográficos
Autor: Sánchez Pla, Àlex|||0000-0002-8673-7737
Tipo de recurso: artículo
Fecha de publicación:1990
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2099/3988
Acceso en línea:https://hdl.handle.net/2099/3988
Access Level:acceso abierto
Palabra clave:Inference
Efficient bootstrap simulation
Centered bootstrap
Linear bootstrap
Balanced bootstrap
Importance Sampling
Antithetic sampling
Delta method
Influence functions
Inferència
Classificació AMS::62 Statistics::62G Nonparametric inference
Descripción
Sumario:Two basic sources of error are associated to the use of bootstrap methods: one is derived from the fact that the true distribution is substituted by a suitable estimate, and the other is simulation errors. Some techniques to reduce or quantify these errors are discussed in this work. Some of them such as importance sampling or antithetic variates are adapted from classical Monte Carlo swindles, whereas others such as the centered and the balanced bootstrap, are more specific. The existence of common methodological trends, such as the use of influence functions and Von Mises expansions to estimate the variance of the methods is emphasized.