Communication in Statistics- Theory and Methods · 2001 · 33 citations · 11 references
Natural SciencesMathematicsEconometricsProbability TheoryStatisticsInferential StatisticsMaximum Likelihood EstimationRobust Statistical ModelingRobust StatisticsStatistical InferenceContinuous Probability DistributionsContinuous Probability SpacesHuber EstimationMaximum Likelihood EstimatorMoment EstimationMoments
Abstract The recently proposed induced cores of continuous probability distributions are briefly introduced and used for a generalization of the classical moment estimation method. The suggested core moment estimators and, if necessary, the Huber moment estimators, are "tailored" to the assumed distributions similarly as the maximum likelihood estimators, with which in some cases coincide. However, the generalized moment estimates are robust. They are in multidimensional cases unexpectedly simple and their asymptotic relative efficiences seem to be reasonably near to one. Keywords: Core functionGeneralized moment methodHuber moment estimates ACKNOWLEDGMENTS The author is deeply indebted to Igor Vajda for valuable suggestions and to anonymous referee whose remarks led to considerable improvement of the paper. The work was supported by grant GA ĈR 201/00/1489.
11
Continuous Univariate Distributions.
Yasuhiro Omori, Norman L. Johnson, S. Kotz et al. · Journal of the American Statistical Association · 1995 · 9.3K citations
Robust Estimation of a Location Parameter
Peter J. Huber · The Annals of Mathematical Statistics · 1964 · 7K citations · Full text
SYSTEMS OF FREQUENCY CURVES GENERATED BY METHODS OF TRANSLATION
Norman L. Johnson · Biometrika · 1949 · 2.2K citations
Loss Models: From Data to Decisions
James D. Broffitt, Stuart A. Klugman, Harry H. Panjer et al. · Journal of the American Statistical Association · 1999 · 1.3K citations
Approximation Theorems of Mathematical Statistics.
R. J. Serfling · Biometrics · 1981 · 1.1K citations