On second order efficiency of a robust test and approximations of its error probabilities. (English) Zbl 0531.62033

In this paper second order efficiency of an asymptotically minimax robust test proposed by H. Rieder [Ann. Stat. 5, 909-921 (1977; Zbl 0371.62074)] is proved. Approximations of the error probabilities of the most powerful robust test obtained by means of second order Edgeworth expansion are compared with simulated values from a normal and a gamma distribution as well as with approximations derived from the asymptotic distribution of this test found in a setting of local alternatives.
Reviewer: H.Büning


62F35 Robustness and adaptive procedures (parametric inference)
62F05 Asymptotic properties of parametric tests
62G20 Asymptotic properties of nonparametric inference


Zbl 0371.62074
Full Text: EuDML


[1] R. R. Bahadur: Some Limit Theorems in Statistics. Society for Industrial and Applied Mathematics, Philadelphia, Pennsylvania 19103. · Zbl 0257.62015
[2] P. J. Bickel D. M. Chibisov, W. R. van Zwet: On efficiency of first and second order. Internat. Statist. Rev. 49 (1981), 169-175. · Zbl 0469.62038
[3] J. Hájek: Sampling from Finite Population. M. Dekker, Inc., New York 1981.
[4] F. R. Hampel: The influence curve and its role in robust estimation. J. Amer. Statist. Assoc. 69 (1974), 383-393. · Zbl 0305.62031
[5] P. J. Huber, V. Strassen: Minimax tests and Neyman-Pearson lemma for capacities. Ann. Statist. 1 (1973), 251-263. · Zbl 0259.62008
[6] H. Rieder: Least favourable pairs for special capacities. Ann. Statist. 5 (1977), 909 - 912. · Zbl 0371.62074
[7] H. Rieder: A robust asymptotic testing model. Ann. Statist. 6 (1978), 1080-1094. · Zbl 0411.62020
[8] J. Stone: Adaptive maximum likelihood estimators of a location parameter. Ann. Statist. 3 (1975), 267-284. · Zbl 0303.62026
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.