Abstract
Minimum Kolmogorov distance estimates of arbitrary parameters are considered. They are shown to be strongly consistent if the parameter space metric is topologically weaker than the metric induced by the Kolmogorov distance of distributions from the statistical model. If the parameter space metric can be locally uniformly upper-bounded by the induced metric then these estimates are shown to be consistent of ordern −1/2. Similar results are proved for minimum Kolmogorov distance estimates of densities from parametrized families where the consistency is considered in theL 1-norm. The presented conditions for the existence, consistency, and consistency of ordern −1/2 are much weaker than those established in the literature for estimates with similar properties. It is shown that these assumptions are satisfied e.g. by all location and scale models with parent distributions different from Dirac, and by all standard exponential models.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Beran R (1977) Minimum Hellinger distance estimates for parametric models. Ann Statist 5:445–463
Beran R (1978) An efficient and robust adaptive estimator of location. Ann Statist 6:292–313
Beran R (1981) Efficient robust estimates in parametric models. Z Wahrsch verw Geb 55:91–108
Blyth CR (1970) On the inference and decision models of statistics. Ann Math Statist 41:1034–1058
Boos DD (1981) Minimum distance estimator for location and goodness of fit. J Amer Statist Assoc 76:663–670
Čencov NN (1982) Statistical decision rules and optimal inference. Translations of Mathem Monographs 53, Amer Math Soc, Providence Rhode Island
Devroye L, Györfi L (1985) Nonparametric density estimation: TheL 1-View. Wiley New York
Donoho DL, Liu RC (1988) The “automatic” robustness of minimum distance functionals. Ann Statist 16:552–586
Dvoretzky A, Kiefer A, Wolfowitz J (1965) Asymptotic minimax character of a sample distribution function and the classical multinomial estimator. Ann Math Statist 33:642–669
Feller W (1966) An introduction to probability theory and its applications, vol II. Wiley New York
Györfi L, Vajda I, van der Meulen E (1994a) Parameter estimation by projecting on structural statistical models. Asymptotic Statistics Proc 5th Prague Conf on Asympt Statist (Mandl P, Hušková (Ed)) 261–272. Physica Verlag Wien
Györfi L, Vajda I, van der Meulen E (1994b) Minimum Hellinger distance point estimates consistent under weak family regularity. Mathem Methods of Statistics 3: 25–45
Györfi L, Vajda I, van der Meulen E (1994c) Density estimation within a parametric family. Trans of 12th Prague Conf on Inform Theory, Statist Dec Functions and Random Processess 91–94. Academy of Sci of Czech Republic and Charles University Prague
Le Cam L (1970) On the assumptions to prove the asymptotic normality of maximum likelihood estimates. Ann Math Statist 41/3:802–828
Liese F, Vajda I (1987) Convex statistical distances. Teubner Leipzig
Lindsay BG (1994) Efficiency versus robustness: The case for minimum Hellinger distance and related methods. Ann Statist 22/2:1081–1114
Massart P (1990) The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality. Ann Probab 18:1269–1283
Marshall AW, Olkin I (1979) Inequalities: Theory of majorization and its applications. Academic Press New York
Millar PW (1981) Robust estimation via minimum distance methods. Z Wahrsch verw Geb 55:73–89
Parr WC, Schucany WR (1980) Minimum distance and robust estimation. J Amer Statist Assoc 75:616–624
Rao CR (1973) Linear statistical inference and its applications, 2nd edition. Wiley New York
Rao PV, Schuster EF, Littell RC (1975) Estimation of a shift and center of symmetry based on Kolmogorov-Smirnov statistics. Ann Statist 3:862–873
Schuster EF, Navarte JA (1973) A new non-parametric estimator of the center of a symmetric distribution. Ann Statist 1:1096–1104
Simpson DG (1987) Minimum Hellinger distance estimation for analysis of count data. J Amer Statist Assoc 82:802–807
Tamura RN, Boos DD (1986) Minimum Hellinger distance estimation for multivariate location and covariance. J Amer Statist Assoc 81:223–229
Author information
Authors and Affiliations
Additional information
Supported by the scientific exchange program between the Hungarian Academy of Sciences and the Royal Belgian Academy of Sciences, and by GACR grant 201/93/0232.
Rights and permissions
About this article
Cite this article
Györfi, L., Vajda, I. & van der Meulen, E. Minimum kolmogorov distance estimates of parameters and parametrized distributions. Metrika 43, 237–255 (1996). https://doi.org/10.1007/BF02613911
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02613911