en
Scientific article
Open access
English

Accurate and robust tests for indirect inference

Published inBiometrika, vol. 97, no. 3, p. 621-630
Collection
  • Open Access - Licence nationale Oxford University Press
Publication date2010
Abstract

In this paper we propose accurate parameter and over-identification tests for indirect inference. Under the null hypothesis the new tests are asymptotically χ2-distributed with a relative error of order n−1. They exhibit better finite sample accuracy than classical tests for indirect inference, which have the same asymptotic distribution but an absolute error of order n−1/2. Robust versions of the tests are also provided. We illustrate their accuracy in nonlinear regression, Poisson regression with overdispersion and diffusion models.

Keywords
  • Indirect inference
  • M-estimator
  • Nonlinear regression
  • Overdispersion
  • Parameter test
  • Robust estimator
  • Saddlepoint test
  • Sparsity
  • Test for over-identification
Citation (ISO format)
CZELLAR, Veronika, RONCHETTI, Elvezio. Accurate and robust tests for indirect inference. In: Biometrika, 2010, vol. 97, n° 3, p. 621–630. doi: 10.1093/biomet/asq040
Main files (1)
Article (Published version)
Identifiers
ISSN of the journal0006-3444
595views
144downloads

Technical informations

Creation09/12/2012 7:23:00 PM
First validation09/12/2012 7:23:00 PM
Update time03/14/2023 5:41:02 PM
Status update03/14/2023 5:41:02 PM
Last indexation05/02/2024 12:39:36 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack