Bandwidth selection for recursive kernel density estimators defined by stochastic approximation method. (English) Zbl 1307.62105
Summary: We propose an automatic selection of the bandwidth of the recursive kernel estimators of a probability density function defined by the stochastic approximation algorithm introduced by A. Mokkadem et al. [J. Stat. Plann. Inference 139, No. 7, 2459–2478 (2009; Zbl 1160.62077)]. We showed that, using the selected bandwidth and the stepsize which minimize the MISE (mean integrated squared error) of the class of the recursive estimators defined in [loc. cit.], the recursive estimator will be better than the nonrecursive one for small sample setting in terms of estimation error and computational costs. We corroborated these theoretical results through simulation study.
Citations:
Zbl 1160.62077Software:
KernSmoothReferences:
| [1] | R. P. W. Duin, “On the choice of smoothing parameters for parzen estimators of probability density functions,” IEEE Transactions on Computers, vol. C-25, no. 11, pp. 1175-1179, 1976. · Zbl 0359.93035 · doi:10.1109/TC.1976.1674577 |
| [2] | M. Rudemo, “Empirical choice of histograms and kernel density estimators,” Scandinavian Journal of Statistics, vol. 9, pp. 65-78, 1982. · Zbl 0501.62028 |
| [3] | D. W. Scott and G. R. Terrell, “Biased and unbiased cross-validation in density estimation,” Journal of the American Statistical Association, vol. 82, pp. 1131-1146, 1987. · Zbl 0648.62037 · doi:10.2307/2289391 |
| [4] | J. S. Marron, “Automatic smoothing parameter selection: a survey,” Empirical Economics, vol. 13, no. 3-4, pp. 187-208, 1988. |
| [5] | M. Woodroofe, “On choosing a delta-sequence,” Annals of Statistics, vol. 41, pp. 1665-1671, 1970. · Zbl 0229.62022 · doi:10.1214/aoms/1177696810 |
| [6] | M. P. Wand and M. C. Jones, Kernel Smoothing, Chapman and Hall, London, UK, 1994. · Zbl 0854.62043 |
| [7] | M. C. Jones, J. S. Marron, and S. J. Sheather, “A brief survey of bandwidth selection for density estimation,” Journal of the American Statistical Association, vol. 91, no. 433, pp. 401-407, 1996. · Zbl 0873.62040 · doi:10.2307/2291420 |
| [8] | J. S. Marron, “Bootstrap bandwidth selection,” in Exploring the Limits of Bootstrap, R. LePage and L. Billard, Eds., pp. 249-262, John Wiley, New York, NY, USA, 1992. · Zbl 0838.62029 |
| [9] | A. Mokkadem, M. Pelletier, and Y. Slaoui, “The stochastic approximation method for the estimation of a multivariate probability density,” Journal of Statistical Planning and Inference, vol. 139, no. 7, pp. 2459-2478, 2009. · Zbl 1160.62077 · doi:10.1016/j.jspi.2008.11.012 |
| [10] | P. Révész, “Robbins-Monro procedure in a Hilbert space and its application in the theory of learning processes I,” Studia Scientiarum Mathematicarum Hungarica, vol. 8, pp. 391-398, 1973. · Zbl 0288.60025 |
| [11] | P. Révész, “How to apply the method of stochastic approximation in the nonparametric estimation of a regression function,” Mathematische Operationsforschung und Statistik, Series Statistics, vol. 8, pp. 119-126, 1977. · Zbl 0369.62098 |
| [12] | A. B. Tsybakov, “Recurrent estimation of the mode of a multidimensional distribution,” Problems of Information Transmission, vol. 8, pp. 119-126, 1990. |
| [13] | Y. Slaoui, “Large and moderate principles for recursive kernel density estimators defined by stochastic approximation method,” Serdica Mathematical Journal, vol. 39, pp. 53-82, 2013. · Zbl 1324.62029 |
| [14] | M. Rosenblatt, “Remarks on some nonparametric estimates of a density function,” The Annals of Mathematical Statistics, vol. 27, pp. 832-837, 1956. · Zbl 0073.14602 · doi:10.1214/aoms/1177728190 |
| [15] | E. Parzen, “On estimation of a probability density and mode,” The Annals of Mathematical Statistics, vol. 33, pp. 1065-1076, 1962. · Zbl 0116.11302 · doi:10.1214/aoms/1177704472 |
| [16] | J. Galambos and E. Seneta, “Regularly varying sequences,” American Mathematical Society, vol. 41, pp. 110-116, 1973. · Zbl 0247.26002 · doi:10.2307/2038824 |
| [17] | R. Bojanic and E. Seneta, “A unified theory of regularly varying sequences,” Mathematische Zeitschrift, vol. 134, no. 2, pp. 91-106, 1973. · Zbl 0256.40002 · doi:10.1007/BF01214468 |
| [18] | A. Mokkadem and M. Pelletier, “A companion for the Kiefer-Wolfowitz-Blum stochastic approximation algorithm,” Annals of Statistics, vol. 35, no. 4, pp. 1749-1772, 2007. · Zbl 1209.62191 · doi:10.1214/009053606000001451 |
| [19] | N. Altman and C. Léger, “Bandwidth selection for kernel distribution function estimation,” Journal of Statistical Planning and Inference, vol. 46, no. 2, pp. 195-214, 1995. · Zbl 0833.62035 · doi:10.1016/0378-3758(94)00102-2 |
| [20] | B. W. Silverman, Density Estimation for Statistics and Data Analysis, Chapman & Hall, London, UK, 1986. · Zbl 0617.62042 |
| [21] | P. Hall and J. S. Marron, “Estimation of integrated squared density derivatives,” Statistics and Probability Letters, vol. 6, no. 2, pp. 109-115, 1987. · Zbl 0628.62029 · doi:10.1016/0167-7152(87)90083-6 |
| [22] | W. Härdle and J. S. Marron, “Optimal bandwidth selection in nonparametric regression function estimation,” Annals of Statistics, vol. 12, pp. 1465-1481, 1985. · Zbl 0594.62043 · doi:10.1214/aos/1176349748 |
| [23] | A. Mokkadem, M. Pelletier, and Y. Slaoui, “Revisiting Révész’s stochastic approximation method for the estimation of a regression function,” ALEA-LatinAmerican Journal of Probability and Mathematical Statistics, vol. 6, pp. 63-114, 2009. · Zbl 1160.62076 |
| [24] | J. D. Hart and P. Vieu, “Data-driven bandwidth choice for density estimation based on dependent data,” Annals of Statistics, vol. 18, pp. 873-890, 1990. · Zbl 0703.62045 · doi:10.1214/aos/1176347630 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
