×

Making robust the cross-validatory choice of smoothing parameter in spline smoothing regression. (English) Zbl 0696.62182

Summary: Cross-validation as a means of choosing the smoothing parameter in spline regression has achieved a wide popularity. Its appeal comprises of an automatic method based on an attractive criterion and along with many other methods it has been shown to minimize predictive mean square error asymptotically. However, in practice there may be a substantial proportion of applications where a cross-validation style choice may lead to drastic undersmoothing often as far as interpolation. Furthermore, because the criterion is so appealing the user may be misled by an inappropriate, automatically-chosen value. In this paper we investigate the nature of cross-validatory methods in spline smoothing regression and suggest variants which provide small sample protection against undersmoothing.

MSC:

62G05 Nonparametric estimation
62G35 Nonparametric robustness
Full Text: DOI

References:

[1] DOI: 10.1007/BF02506337 · Zbl 0259.62076 · doi:10.1007/BF02506337
[2] DOI: 10.1109/TAC.1974.1100705 · Zbl 0314.62039 · doi:10.1109/TAC.1974.1100705
[3] DOI: 10.2307/1267161 · Zbl 0219.62013 · doi:10.2307/1267161
[4] DOI: 10.1007/BF01404567 · Zbl 0377.65007 · doi:10.1007/BF01404567
[5] DOI: 10.1016/0167-7152(84)90029-4 · Zbl 0521.65010 · doi:10.1016/0167-7152(84)90029-4
[6] Eubank R. L., J.R. Statist. Soc. B 47 pp 332– (1985)
[7] Härdle W., Biometrika 72 pp 481– (1985)
[8] DOI: 10.1007/BF01389878 · Zbl 0578.65009 · doi:10.1007/BF01389878
[9] De Hoog F. R., Research Report, Ausralian National University 47 (1985)
[10] Moyeed R. A., Ph.D. Thesis University of Bath 47 (1986)
[11] DOI: 10.1214/aos/1176346788 · Zbl 0554.62035 · doi:10.1214/aos/1176346788
[12] DOI: 10.1093/biomet/68.1.45 · Zbl 0464.62054 · doi:10.1093/biomet/68.1.45
[13] DOI: 10.2307/2288404 · doi:10.2307/2288404
[14] Silverman B. W., J. R. Statis. Soc. B 47 pp 364– (1985)
[15] Speckman P., The asymptotic integrated mean square error for smoothing noisy data by splines (1983)
[16] DOI: 10.1007/BF01463995 · Zbl 0414.65007 · doi:10.1007/BF01463995
[17] DOI: 10.1007/BF01437407 · Zbl 0299.65008 · doi:10.1007/BF01437407
[18] Wahba G., J.R. Statis. Soc.B 40 (1978)
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.