Scientific article

Saddlepoint approximations and tests based on multivariate M -estimates

Published inAnnals of statistics, vol. 31, no. 4, p. 1154-1169
Publication date2003

We consider multidimensional M-functional parameters defined by expectations of score functions associated with multivariate M-estimators and tests for hypotheses concerning multidimensional smooth functions of these parameters. We propose a test statistic suggested by the exponent in the saddlepoint approximation to the density of the function of the M-estimates. This statistic is analogous to the log likelihood ratio in the parametric case. We show that this statistic is approximately distributed as a chi-squared variate and obtain a Lugannani-Rice style adjustment giving a relative error of order . We propose an empirical exponential likelihood statistic and consider a test based on this statistic. Finally we present numerical results for three examples including one in robust regression.

  • Bootstrap tests
  • Composite hypothesis
  • Nonparametric likelihood
  • Relative error
  • Smooth functions of M-estimators
Citation (ISO format)
ROBINSON, J., RONCHETTI, Elvezio, YOUNG, G.A. Saddlepoint approximations and tests based on multivariate M -estimates. In: Annals of statistics, 2003, vol. 31, n° 4, p. 1154–1169. doi: 10.1214/aos/1059655909
Main files (1)
Article (Published version)
ISSN of the journal0090-5364

Technical informations

Creation09/16/2012 7:13:00 PM
First validation09/16/2012 7:13:00 PM
Update time03/14/2023 5:40:59 PM
Status update03/14/2023 5:40:59 PM
Last indexation01/16/2024 12:14:30 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack