Abstract
Given a density f we pose the problem of estimating the density functional \(\psi_r=\int f^{(r)}f\) for a non-negative even r making use of kernel methods. This is a well-known problem but some of its features remained unexplored. We focus on the problem of bandwidth selection. Whereas all the previous studies concentrate on an asymptotically optimal bandwidth here we study the properties of exact, non-asymptotic ones, and relate them with the former. Our main conclusion is that, despite being asymptotically equivalent, for realistic sample sizes much is lost by using the asymptotically optimal bandwidth. In contrast, as a target for data-driven selectors we propose another bandwidth which retains the small sample performance of the exact one.
Similar content being viewed by others
References
Aldershof B (1991) Estimation of integrated squared density derivatives. PhD thesis, University of North Carolina, Chapel Hill
Aldershof B, Marron JS, Park BU, Wand MP (1995) Facts about the Gaussian probability density function. Appl Anal 59:289–306
Bhattacharya GK, Roussas GG (1969) Estimation of a certain functional of a probability density function. Skand Aktuarietidskr 1969:201–206
Bickel PJ, Ritov Y (1988) Estimating integrated squared density derivatives: sharp best order of convergence estimates. Sankhya Ser 50:381–393
Butzer PL, Nessel RJ (1971) Fourier analysis and approximation, vol 1. Birkhäuser, Basel
Chacón JE, Tenreiro C (2011) Data-based choice of the number of pilot stages for plug-in bandwidth selection. To appear in Commun Statist Theory Methods. doi:10.1080/03610926.2011.606486
Chacón JE, Montanero J, Nogales AG (2007a) A note on kernel density estimation at a parametric rate. J Nonparametr Stat 19:13–21
Chacón JE, Montanero J, Nogales AG, Pérez P (2007b) On the existence and limit behavior of the optimal bandwidth for kernel density estimation. Stat Sin 17:289–300
Dmitriev YG, Tarasenko FP (1973) On the estimation of functionals of the probability density and its derivatives. Theory Probab Appl 18:628–633
Dmitriev YG, Tarasenko FP (1975) On a class of non-parametric estimates of non-linear functionals of density. Theory Probab Appl 19:390–394
Giné E, Mason DM (2008) Uniform in bandwidth estimation of integral functionals of the density function. Scand J Statist 35:739–761
Giné E, Nickl R (2008) A simple adaptive estimator of the integrated square of a density. Bernoulli 14:47–61
Hall P, Marron JS (1987) Estimation of integrated squared density derivatives. Stat Probab Lett 6:109–115
Hettmansperger TP (1984) Statistical inference based on ranks. Wiley, New York
Hewitt E, Stromberg K (1965) Real and abstract analysis. Springer, Berlin
Jones MC, Sheather SJ (1991) Using non-stochastic terms to advantage in kernel-based estimation of integrated squared density derivatives. Stat Probab Lett 11:511–514
Laurent B (1997) Estimation of integral functionals of a density and its derivatives. Bernoulli 3:181–211
Levit BY (1978) Asymptotically efficient estimation of nonlinear functionals. Probl Inf Transm 14:65–72
Marron JS, Wand MP (1992) Exact mean integrated squared error. Ann Stat 20:712–736
Politis DN, Romano JP (1999) Multivariate density estimation with general flat-top kernels of infinite order. J Multivar Anal 68:1–25
Prakasa Rao BLS (1983) Nonparametric functional estimation. Academic, New York
Prakasa Rao BLS (1999) Estimation of the integrated squared density derivatives by wavelets. Bull Inform Cybern 31:47–65
Scott DW (1992) Multivariate density estimation: theory, practice and visualization. Wiley, New York
Schuster EF (1974) On the rate of convergence of an estimate of a functional of a probability density. Scand Actuar J 1974:103–107
Sheather SJ, Hettmansperger TP, Donald MR (1994) Data-based bandwidth selection for kernel estimators of the integral of f 2(x). Scand J Statist 21:265–275
Tenreiro, C (2003) On the asymptotic normality of multistage integrated density derivatives kernel estimators. Stat Probab Lett 64:311–322
van Es B (1992) Estimating functionals related to a density by a class of statistics based on spacings. Scand J Statist 19:61–72
Wand MP, Jones MC (1995) Kernel smoothing. Chapman and Hall, London
Wand MP, Schucany WR (1990) Gaussian-based kernels. Can J Stat 18:197–204
Wu T-J (1995) Adaptive root n estimates of integrated squared density derivatives. Ann Stat 23:1474–1495
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chacón, J.E., Tenreiro, C. Exact and Asymptotically Optimal Bandwidths for Kernel Estimation of Density Functionals. Methodol Comput Appl Probab 14, 523–548 (2012). https://doi.org/10.1007/s11009-011-9243-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11009-011-9243-x