Abstract
Starting from the classical theorem of Weierstrass (and its modifications) on approximation of continuous functions by means of Bernstein polynomials a smoothed histogram type estimator is developed for estimating probability densities and its derivatives. Consistency results are obtained in form of various strong laws. In particular, one gets estimates for the rates for pointwise and uniform strong convergence of estimators for the derivatives. Moreover, for approximating the density itself the exact order of consistency is established. This is done by a law of iterated logarithm for pointwise approximation and by a law of logarithm in case of uniform approximation.
Similar content being viewed by others
References
P. L. Butzer, On the extension of Bernstein polynomials to the infinite interval,Proc. Amer. Math. Soc. 5 (1954), 547–553.MR 16, 128
P. L. Butzer, Summability of generalized Bernstein polynomials, I,Duke Math. J. 22 (1955), 617–623.MR 17, 476
M. Csörgő,Gaussian processes, strong approximations, an interplay, Ruhr-Universität, Bochum, 1980. (Lecture notes)
M. Csörgő andA. H. C. Chan, On the Erdős—Rényi increments and the P. Lévy modulus of continuity of a Kiefer process,Empirical distributions and processes (Meeting, Oberwolfach, 1976) (Lecture Notes in Mathematics, 566) Springer, Berlin, 1976; 17–32.MR 56: 1424
M. Csörgő andP. Révész,Strong approximations in probability and statistics, Academic Press, New York, 1981.MR 84d: 60050
J. Favard, Sur les multiplicateurs d'interpolation,J. Math. Pures Appl. 23 (1944), 219–247.MR 7, 436
W. Feller,An introduction to probability theory and its applications, second edition, Wiley, New York, 1971.MR 35: 1048,42: 5292
A. Földes andP. Révész, A general method for density estimation,Studia Sci. Math. Hungar. 9 (1974), 81–92.MR 51: 9338
W. Gawronski,Verallgemeinerte Bernsteinfunktionen und Schätzung einer Wahrscheinlichkeitsdichte, Universität Ulm, 1980. (Habilitationsschrift)
W. Gawronski andU. Stadtmüller, On density estimation by means of Poisson's distribution,Scand. J. Statist. 7 (1980), 90–94.MR 81j: 62090
W. Gawronski andU. Stadtmüller, Smoothing histograms by means of lattice and continuous distributions,Metrika 28 (1981), 155–164.MR 82k: 62075
W. Gawronski andU. Stadtmüller, Approximation of continuous functions by generalized Favard operators,J. Approx. Theory 34 (1982), 384–396.
W. Gawronski andU. Stadtmüller, Linear combinations of iterated generalized Bernstein functions with an application to density estimation,Acta Sci. Math. (Szeged)47 (1984), 205–221.
P. Hall, Laws of the iterated logarithm for nonparametric density estimators,Z. Wahrsch. Verw. Gebiete 56 (1981), 47–61.MR 82e: 60049
J. Komlós, P. Major andG. Tusnády, An approximation of partial sums of independent RV's and the sample DF, I,Z. Wahrsch. Verw. Gebiete 32 (1975), 111–131.MR 51: 11605b
G. G. Lorentz,Bernstein polynomials, University of Toronto Press, Toronto, 1953.MR 15, 217
V. V. Petrov, Summy nezavisimyh slučainyh velicin43-1 (Sums of independent random variables)}, Nauka, Moskva, 1972.MR 48: 1288
V. V. Petrov,Sums of independent random variables, Springer, Berlin, 1975.MR 52: 9335
R.-D. Reiss, Consistency of a certain class of empirical density functions,Metrika 22 (1975), 189–203.MR 52: 15823
P. Révész, A strong law of the empirical density function,Period. Math. Hungar. 9 (1978), 317–324.MR 80b: 60047
P. Révész,How to characterize the asymptotic properties of a stochastic process by four classes of deterministic curves? Carleton Math. Series, No. 164, 1980.
B. W. Silverman, Weak and strong uniform consistency of the kernel estimate of a density and its derivatives,Ann. Statist. 6 (1978), 177–184.MR 57: 10904
U. Stadtmüller, Asymptotic distributions of smoothed histograms,Metrika 30 (1983), 145–158.
W. Stute, The oscillation behaviour of empirical processes,Ann. Prob. 10 (1982), 86–117.MR 83e: 60028
W. Stute, A law of the logarithm for kernel density estimators,Ann. Prob. 10 (1982), 414–422.MR 84c: 62060
O. Szász, Generalization of S. Bernstein's polynomials to the infinite interval,J. Research Nat. Bur. Standards 45 (1950), 239–245.MR 13, 648
R. Vitale, A Bernstein polynomial approach to density estimation,Statistical inference and related topics, Academic Press, New York, 1975; 87–99.MR 53: 1832
H. Walk,Approximation unbeschränkter Funktionen durch lineare positive Operatoren, Universität Stuttgart, 1970. (Habilitationsschrift)
H. Walk, Lokale Approximation unbeschränkter Funktionen und ihrer Ableitungen durch eine Klasse von Folgen linearer positiver Operatoren,Mathematica (Cluj)15 (1973), 129–142.MR 52: 6266
G. G. Walter andJ. R. Blum, Probability density estimation using delta sequences,Ann. Statist. 7 (1979), 328–340.MR 81b: 62057
B. B. Winter, Rate of strong uniform consistency of nonparametric density estimators,Studia Sci. Math. Hungar. 11 (1976), 283–295.MR 80k: 62060
Author information
Authors and Affiliations
Additional information
This paper contains parts of the author's “Habilitationsschrift” written at the Department of Mathematics of the University of Ulm.
Rights and permissions
About this article
Cite this article
Gawronski, W. Strong laws for density estimators of bernstein type. Period Math Hung 16, 23–43 (1985). https://doi.org/10.1007/BF01855801
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01855801