Abstract
A modification of the fast algorithm for the bandwidth selection of kernel functions in a nonparametric probability density estimate of the Rosenblatt–Parzen type is proposed. Fast algorithms for optimizing kernel estimates of probability densities make it possible to significantly reduce the calculation time when selecting their smoothing parameters (bandwidths) in comparison with the traditional approach, which is especially important when processing large statistical data. The method is based on the analysis of the formula for the optimal calculation of the smoothing parameter of kernel functions and the discovered dependence between the nonlinear functional on the second derivative of the reconstructed probability density and the antikurtosis coefficient. The proposed algorithm for the bandwidth selection provides a decrease in the probability density approximation error in comparison with the traditional approach. The findings are confirmed by the results of computational experiments. Special attention is paid to the dependence of these properties on the amount of initial data.
Similar content being viewed by others
REFERENCES
M. Rudemo, ‘‘Empirical choice of histogram and kernel density estimators,’’ Scand. J. Stat. 9, 65–78 (1982).
A. W. Bowman, ‘‘A comparative study of some kernel-based non-parametric density estimators,’’ J. Stat. Comput. Simul. 21, 313–327 (1982). https://doi.org/10.1080/00949658508810822
P. Hall, ‘‘Large-sample optimality of least squares cross-validation in density estimation,’’ Ann. Statist. 1983. 11 (4), 1156–1174.
A. V. Lapko and V. A. Lapko, ‘‘Analysis of optimization methods for nonparametric estimation of the probability density with respect to the blur factor of kernel functions,’’ Meas. Tech. 60, 515–522 (2017). https://doi.org/10.1007/s11018-017-1228-x
E. S. Nezhevenko, ‘‘Neural network classification of difficult-to-distinguish types of vegetation on the basis of hyperspectral features,’’ Optoelectron., Instrum. Data Process. 55, 263–270 (2019). https://doi.org/10.3103/S8756699019030087
A. V. Lapko, V. A. Lapko, S. T. Im, V. P. Tuboltsev, and V. A. Avdeenok, ‘‘Nonparametric algorithm of identification of classes corresponding to single-mode fragments of the probability density of multidimensional random variables,’’ Optoelectron., Instrum. Data Process. 55, 230–236 (2019). https://doi.org/10.3103/S8756699019030038
A. V. Lapko and V. A. Lapko, ‘‘A technique for testing hypotheses for distributions of multidimensional spectral data using a nonparametric pattern recognition algorithm,’’ Comput. Optics 43, 238–244 (2019). https://doi.org/10.18287/2412-6179-2019-43-2-238-244
S. M. Borzov and O. I. Potaturkin, ‘‘Spectral-spatial methods for hyperspectral image classification. Review,’’ Optoelectron., Instrum. Data Process. 54, 582–599 (2018). https://doi.org/10.3103/S8756699018060079
A. V. Lapko and V. A. Lapko, ‘‘Fast algorithm for choosing kernel function blur coefficients in a nonparametric probability density estimate,’’ Meas. Tech. 61, 540–545 (2018). https://doi.org/10.32446/0368-1025it-2018-6-16-20
A. V. Lapko and V. A. Lapko, ‘‘Fast selection of blur coefficients in a multidimensional nonparametric pattern recognition algorithm,’’ Meas. Techn. 62, 665–672 (2018). https://doi.org/10.32446/0368-1025it.2018-10-19-23
A. V. Lapko and V. A. Lapko, ‘‘Integral estimate from the square of the probability density for a one-dimensional random variable,’’ Meas. Tech. (2020). doi 10.1007/s11018-020-01820-1
D. W. Scott, Multivariate Density Estimation: Theory, Practice, and Visualization (John Wiley & Sons, New Jersey, 2015). https://doi.org/10.1002/9780470316849
A. V. Lapko and V. A. Lapko, ‘‘Dependencies between histogram parameters and the kernel estimate of the probability density of a multidimensional random variable,’’ Meas. Tech. 62, 945–952 (2020). https://doi.org/10.32446/0368-1025it.2019-9-3-8
V. A. Epanechnikov, ‘‘Non-Parametric Estimation of a Multivariate Probability Density,’’ Theory Probab. Its Appl. 14, 153–158 (1969).
A. S. Sharakshane, I. G. Zheleznov, and V. A. Ivnitskii, Complex Systems (Vysshaya Shkola, Moscow, 1977).
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated by I. Obrezanova
About this article
Cite this article
Lapko, A.V., Lapko, V.A. Modified Fast Algorithm for the Bandwidth Selection of the Kernel Density Estimation. Optoelectron.Instrument.Proc. 56, 566–572 (2020). https://doi.org/10.3103/S8756699020060102
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S8756699020060102