Smoothing Techniques for Curve Estimation

M. Rosenblatt

ISBN 10: 3540097066 / ISBN 13: 9783540097068

Verlag: Springer Berlin Heidelberg, Springer Berlin Heidelberg Nov 1979, 1979

Beschreibung

Neuware -Nonparametric curve estimation.- A tree-structured approach to nonparametric multiple regression.- Kernel estimation of regression functions.- Total least squares.- Some theoretical results on Tukey¿s 3R smoother.- Bias- and efficiency-robustness of general M-estimators for regression with random carriers.- Approximate conditional-mean type smoothers and interpolators.- Optimal convergence properties of kernel estimates of derivatives of a density function.- Density quantile estimation approach to statistical data modelling.- Global measures of deviation for kernel and nearest neighbor density estimates.- Some comments on the asymptotic behavior of robust smoothers.- Cross-validation techniques for smoothing spline functions in one or two dimensions.- Convergence rates of 'thin plate' smoothing splines wihen the data are noisy. 256 pp. Englisch.

Bestandsnummer des Verkäufers 9783540097068

Bibliografische Details

• Titel: Smoothing Techniques for Curve Estimation
• Verlag: Springer Berlin Heidelberg, Springer Berlin Heidelberg Nov 1979
• Erscheinungsjahr: 1979
• Sprache: Englisch
• ISBN-10: 3540097066
• ISBN-13: 9783540097068
• Einband: Taschenbuch
• Zustand: Neu
• Abmessungen: 235B x 155 H x 15 T Millimeter Breite: 235 mm, Höhe: 155 mm, Tiefe: 15 mm
• Gewicht: 394 Gramm