According to Efron and Tibshirani (1993), the traditional road to statistical knowledge is blocked, for most, by a formidable wall of mathematics. The usefulness of the bootstrap method is particularly appreciable when dealing with complex estimators or non-smooth statistics. Our work is intended to find out if bootstrap methods other than the standard bootstrap can be satisfactory used to break a “thicker wall”: the dependence in data structure. In this paper we present some variants of existing bootstrap methods for complex surveys and nested multilevel models.
Refining bootstrap methods in dependent data structures : is there room for improvement? / Manzi, G.. - (2010). (Intervento presentato al convegno Royal statistical society conference tenutosi a Brighton).
Refining bootstrap methods in dependent data structures : is there room for improvement?
G. Manzi
2010
Abstract
According to Efron and Tibshirani (1993), the traditional road to statistical knowledge is blocked, for most, by a formidable wall of mathematics. The usefulness of the bootstrap method is particularly appreciable when dealing with complex estimators or non-smooth statistics. Our work is intended to find out if bootstrap methods other than the standard bootstrap can be satisfactory used to break a “thicker wall”: the dependence in data structure. In this paper we present some variants of existing bootstrap methods for complex surveys and nested multilevel models.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
