Statistical Papers

, Volume 53, Issue 1, pp 1–21 | Cite as

Consistency of the kernel density estimator: a survey

Survey Article

Abstract

Various consistency proofs for the kernel density estimator have been developed over the last few decades. Important milestones are the pointwise consistency and almost sure uniform convergence with a fixed bandwidth on the one hand and the rate of convergence with a fixed or even a variable bandwidth on the other hand. While considering global properties of the empirical distribution functions is sufficient for strong consistency, proofs of exact convergence rates use deeper information about the underlying empirical processes. A unifying character, however, is that earlier and more recent proofs use bounds on the probability that a sum of random variables deviates from its mean.

Keywords

Kernel estimation Pointwise consistency Strong uniform consistency Empirical process Rate of convergence Variable bandwidth 

Mathematics Subject Classification (2000)

60-02 62-02 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Büning H, Trenkler G (1994) Nichtparametrische Statistische Methoden, 2nd edn. de Gruyter, BerlinMATHGoogle Scholar
  2. Deheuvels P, Mason D (2004) General asymptotic confidence bands based on kernel-type function estimators. Stat Inference Stoch Proces 7: 225–277MathSciNetMATHCrossRefGoogle Scholar
  3. Dette H, Gefeller O (1995) Definitions of nearest neighbour distances for censored data on the nearest neighbour kernel estimators of the hazard rate. J Nonparametr Stat 4: 271–282MathSciNetMATHCrossRefGoogle Scholar
  4. Diehl S, Stute W (1988) Kernel density and hazard function estimation in the presence of censoring. J Multivar Anal 25: 299–310MathSciNetMATHCrossRefGoogle Scholar
  5. Dvoretzky A, Kiefer J, Wolfowitz J (1956) Asymptotic minimax character of the sample distribution function and of the classical multinomial estimator. Annal Math Stat 27: 642–669MathSciNetMATHCrossRefGoogle Scholar
  6. Einmahl U, Mason D (2005) Uniform in bandwidth consistency of kernel-type function estimators. Annal Stat 33: 1380–1403MathSciNetMATHCrossRefGoogle Scholar
  7. Hall P (1978) Cross-validation in density estimation. Biometrika 69: 383–390CrossRefGoogle Scholar
  8. Hall P, Marron J (1995) Improved variable window kernel estimates of probability densities. Annal Stat 23: 1–10MathSciNetMATHCrossRefGoogle Scholar
  9. Hall P, Sheather S, Jones M, Marron J (1991) On optimal data-based bandwidth selection in kernel density estimation. Biometrika 78: 263–269MathSciNetMATHCrossRefGoogle Scholar
  10. Härdle W (1991) Smoothing techniques. Springer, New YorkMATHCrossRefGoogle Scholar
  11. Marron J, Gonzàlez-Manteiga W, Cao R (1996) Bootstrap selection of the smoothing parameter in nonparametric hazard rate estimation. J Am Stat Assoc 91: 1130–1140MATHCrossRefGoogle Scholar
  12. Massart P (1990) The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality. Annal Probab 18: 1269–1283MathSciNetMATHCrossRefGoogle Scholar
  13. Nadaraja E (1964) On estimating regression. Theory Probabil Appl 9(1): 141–142CrossRefGoogle Scholar
  14. Nadaraja E (1965) On nonparametric estimates of density functions and regression curves. Theory Probabil Appli 10: 186–190MathSciNetCrossRefGoogle Scholar
  15. Parzen E (1962) On estimation of a probability density function and mode. Annal Math Stat 33: 1065–1076MathSciNetMATHCrossRefGoogle Scholar
  16. Rosenblatt M (1956) Remarks on some nonparametric estimates of a density function. Annal Math Stat 27: 832–835MathSciNetMATHCrossRefGoogle Scholar
  17. Schäbe H, Tiedge J (1995) Kernel estimation for characteristics of pure jump processes. Stat Paper 36: 131–144MATHCrossRefGoogle Scholar
  18. Schäfer H (1986) Local convergence of empirical measures in the random censorship situation with application to density and rate estimators. Annal Stat 14: 1240–1245MATHCrossRefGoogle Scholar
  19. Silverman B (1986) Density estimation. Chapman and Hall, LondonMATHGoogle Scholar
  20. Stute W (1982a) A law of the logarithm for kernel density estimators. Annal Probabil 10: 414–422MathSciNetMATHCrossRefGoogle Scholar
  21. Stute W (1982b) The oscillation behavior of empirical processes. Annal Probabil 10: 86–107MathSciNetMATHCrossRefGoogle Scholar
  22. Stute W (1984) The oscillation behavior of empirical processes: The multivariate case. Annal Probabil 12: 361–379MathSciNetMATHCrossRefGoogle Scholar
  23. Talagrand M (1994) Sharper bounds for gaussian and empirical processes. Annal Probabil 22: 28–76MathSciNetMATHCrossRefGoogle Scholar
  24. Wagner T (1975) Nonparametric estimates of probability densities. IEEE Trans Inf Theory 21: 438–440MATHCrossRefGoogle Scholar
  25. Wand M, Jones M (1995) Kernel smoothing. Chapman and Hall, LondonMATHGoogle Scholar
  26. Watson G (1964) Smooth regression analysis. Sankhya A 26: 101–116MATHGoogle Scholar
  27. Weißbach R (2006) A general kernel functional estimator with general bandwidth—strong consistency and applications. J Nonparametr Stat 18: 1–12MathSciNetMATHCrossRefGoogle Scholar
  28. Weißbach R, Pfahlberg A, Gefeller O (2008) Double-smoothing in kernel hazard rate estimation. Method Inf Med 47: 167–173Google Scholar
  29. Wheeden R, Zygmund A (1977) Measure and integral—an introduction to real analysis. Marcel Dekker, New YorkMATHGoogle Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  1. 1.Institut für Wirtschafts- und SozialstatistikTechnische Universität DortmundDortmundGermany
  2. 2.Lehrstuhl für Statistik, Institut für VolkswirtschaftslehreUniversität RostockRostockGermany

Personalised recommendations