Bootstrap almost goodness-of-fit tests

A. Baíllo Moreno, J. Cárcamo Urtiaga

The almost goodness-of-fit test is a procedure to decide if a (parametric) model serves as a good representation of the probability distribution generating the sample. We use the M-estimator of the parameters to determine the approximating model (within the parametric class) to the unknown distribution. The main objective is the approximate validation of a distribution or an entire parametric family up to a pre-specified margin of error. The test statistic is the Lp-distance between the empirical distribution function and the corresponding one of the estimated (parametric) model. The rejection region is determined via an easy-to-implement and flexible bootstrap method.

Palabras clave: Bootstrap; Empirical process; Goodness-of-fit; Model validation

Estadística no paramétrica I
12 de junio de 2025  15:30
Sala de prensa (MR 13)

P. De La Lama, J. A. Martin Fernandez, M. Comas Cufi

Á. Herce Postigo, M. J. Salvador Figueras

A. García Nogales

V. Peña Pizarro, A. Duarte-López, M. Pérez Casany