Abstract
This paper investigates the local robustness properties of a general class of multidimensional tests based on M-estimators. These tests are shown to inherit the efficiency and robustness properties of the estimators on which they are based. In particular, it is shown that small perturbations of the distribution of the observations can have arbitrarily large effects on the asymptotic level and power of tests based on estimators that do not possess a bounded influence function. An asymptotic ‘admissibility’ result is also presented, which provides a justification for tests based on optimal bounded-influence estimators.
Publisher
Cambridge University Press (CUP)
Subject
Economics and Econometrics,Social Sciences (miscellaneous)
Reference25 articles.
1. Approximation Theorems of Mathematical Statistics
2. A new infinitesimal approach to robust estimation
3. 19. Ronchetti E. Robust testing in linear models: The infinitesimal approach, unpublished Ph.D. Thesis, ETH, Zurich, 1982.
4. A Robust Asymptotic Testing Model
Cited by
18 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Accurate and robust inference;Econometrics and Statistics;2020-04
2. Robust composite binary hypothesis testing via measure-transformed quasi score test;Signal Processing;2019-02
3. A robust test of exogeneity based on quantile regressions;Journal of Statistical Computation and Simulation;2017-05-04
4. Robust Estimation of Heckman Model;Robustness in Econometrics;2017
5. Robust inference in sample selection models;Journal of the Royal Statistical Society: Series B (Statistical Methodology);2015-11-20