# zbMATH — the first resource for mathematics

Efficiency and robustness control via distorted maximum likelihood estimation. (English) Zbl 0603.62039
In the present paper distorted maximum likelihood estimators (M.L.E.’s), denoted by $$T^{\alpha}$$, with a distortion parameter $$\alpha\geq 0$$ are introduced so that $$T^ 0$$ is the classical nondistorted M.L.E. The M.L.E. is known to be efficient but not robust, whereas the distorted estimators are shown to be robust but not efficient. For quite general types of distortion and statistical families, the distorted estimates as well as the corresponding influence curves and asymptotic variances are shown to be continuous at $$\alpha =0$$. Thus the parameter $$\alpha$$ controls the efficiency and robustness of the estimators under consideration, so that one can easily review the set of attainable compromises and select the most appropriate one. This possibility is analyzed in more detail with respect to two concrete families of distorted M.L.E.’s.
Reviewer: H.Büning

##### MSC:
 62F35 Robustness and adaptive procedures (parametric inference) 62F12 Asymptotic properties of parametric estimators
Full Text:
##### References:
 [1] J. Anděl: Mathematical Statistics. (in Czech). SNTL - ALFA, Praha-Bratislava 1978. [2] T. W. Anderson: The integral of a symmetric unimodal function over a symmetric convex set and some probability inequalities. Proc. Amer. Math. Soc. 6 (1955), 170- 176. · Zbl 0066.37402 · doi:10.2307/2032333 [3] R. A. Fisher: On the mathematical foundations of theoretical statistics. Reprinted in: Contributions to Mathematical Statistics (by R. A. Fisher). J. Wiley, New York 1950. [4] W. Fuller: Introduction to the Statistical Time Series. J. Wiley, New York 1976. · Zbl 0353.62050 [5] F. R. Hampel: The influence curve and its role in robust estimation. J. Amer. Statist. Assoc. 69 (1974), 383-393. · Zbl 0305.62031 · doi:10.2307/2285666 [6] P. I. Huber: Robust estimation of a location parameter. Ann. Math. Statist. 35 (1964), 73-101. · Zbl 0136.39805 · doi:10.1214/aoms/1177703732 [7] J. L. Kelley: General Topology. Van Nostrand, Princeton 1957. · Zbl 0157.53002 [8] L. Le Cam: On the asymptotic theory of estimation and testing hypotheses. Proc. 3rd Berkeley Symp. Math. Statist. Prob. Vol. 1 (1956), 129-156. [9] A. Perez: Notions generalisées d’incertitude, d’entropie et d’information du point de vue de la théorie des martingales. Trans. 1st Prague Conf. on Inform. Theory, etc. Publ. House Czechosl. Acad. Sci., Prague 1957. · Zbl 0102.13204 [10] J. Pfanzagl: On the measurability and consistency of minimum contrast estimators. Metrika 14 (1969), 249-272. · Zbl 0181.45501 · doi:10.1007/BF02613654 · eudml:175401 [11] J. Pfanzagl: The second order optimaiity of tests and estimators for minimum contrast functional. Probab. and Math. Statist. 2 (1981), 55 - 70. · Zbl 0523.62039 [12] A. Rényi: Theory of probability. (in Czech). Academia, Prague 1972. [13] I. Vajda: Motivation, existence and equivariance of D-estimators. Kybernetika 20 (1984), 189-208. · Zbl 0558.62026 · eudml:28738 [14] I. Vajda: Robust estimation in discrete and continuous families by means of a minimum chi-square method. Problems Control Inform. Theory 15 (1986), No. 2. · Zbl 0609.62053
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.