×

An iterative bandwidth selector for kernel estimation of densities and their derivatives. (English) Zbl 1380.62146

Summary: A bandwidth selection rule which proved to be useful and effective for nonparametric kernel regression is modified to be suitable for estimation of a density and its derivatives. Various versions of the rule are considered. Theoretical properties are derived. A simulation study compares its finite-sample behavior with that of other bandwidth selectors.

MSC:

62G07 Density estimation
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Brockmann M., JASA 88 (1993)
[2] Gasser T., J. Royal Statist. Soc. B 47 pp 238– (1985)
[3] DOI: 10.2307/2290393 · Zbl 0733.62047 · doi:10.2307/2290393
[4] DOI: 10.1093/biomet/79.4.783 · Zbl 0765.62044 · doi:10.1093/biomet/79.4.783
[5] Herrmann E., JRSS-B to appear (1993)
[6] DOI: 10.1007/BF00363516 · Zbl 0588.62052 · doi:10.1007/BF00363516
[7] Härdle W., J. R.Statist. Soc. B 52 pp 223– (1990)
[8] DOI: 10.1007/BF01192160 · Zbl 0742.62041 · doi:10.1007/BF01192160
[9] DOI: 10.1007/BF01205233 · Zbl 0742.62042 · doi:10.1007/BF01205233
[10] DOI: 10.1093/biomet/78.2.263 · Zbl 0733.62045 · doi:10.1093/biomet/78.2.263
[11] DOI: 10.1214/aos/1176348378 · Zbl 0745.62033 · doi:10.1214/aos/1176348378
[12] Jones M. C., Progress in data-based bandwidth selection for kernel density estimation, Working Paper 92-014 (1992)
[13] DOI: 10.1016/0167-7152(91)90116-9 · Zbl 0724.62040 · doi:10.1016/0167-7152(91)90116-9
[14] DOI: 10.1214/aos/1176348653 · Zbl 0746.62040 · doi:10.1214/aos/1176348653
[15] DOI: 10.2307/2289526 · doi:10.2307/2289526
[16] Sheather S., J. R. Statistic. Soc. B 53 pp 683– (1991)
[17] DOI: 10.2307/2289786 · doi:10.2307/2289786
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.