Abstract
We discuss a nonparametric regression model on an equidistant grid of the real line. A class of kernel type estimates based on the so-called fundamental cardinal splines will be introduced. Asymptotic optimality of these estimates will be established for certain functional classes. This model explains the often mentioned heuristic fact that cubic splines are adequate for most practical applications.
Similar content being viewed by others
References
N. I. Akhiezer, Theory of Approximation (Frederick Ungar Publ., New York, 1956).
L. Artiles and B. Levit, “Adaptive Regression on the Real Line in Classes of Smooth Functions”, Austrian J. Statist. 32, 99–129 (2003).
R. L. Eubank, Spline Smoothing and Nonparametric Regression, 2nd ed. (Marcel Dekker, New York, 1999).
W. Feller, An Introduction to Probability Theory and Its Applications, (Wiley, New York, 1966), Vol. II.
O. Lepski and B. Levit, “Adaptive Minimax Estimation of Infinitely Differentiable Functions”, Math. Methods Statist. 7, 123–156 (1998).
M. J. Marsden, F. B. Richards, and S. D. Riemenschneider, “Cardinal Spline Interpolation Operators on l p Data”, J. Math., Indiana Univ. 24, 667–689 (1975).
C. A. Micchelli, “Infinite Spline Interpolation”, in Approximation in Theorie and Praxis (Bibliographisches Institute, Mannheim, 1979), pp. 209–238.
M. Reimer, “The Main Roots of the Euler-Frobenius Polynomials”, J. Approximation Theory 45, 358–362 (1985).
I. J. Schoenberg, Cardinal Spline Interpolation (SIAM, New York, 1973).
I. J. Schoenberg, “Cardinal Interpolation and Spline Functions, II”, J. Approximation Theory 6, 404–420 (1974).
I. J. Schoenberg, Selected Papers, Ed. by Carl de Boor (Birkhäuser, Boston, 1988).
I. J. Schoenberg and A. Sharma, “The Interpolatory Background of the Maclaurin Quadrature Formula”, Bull. Amer. Math. Soc. 77, 1034–1038 (1971).
L. L. Schumaker, Spline Functions: Basic Theory (Wiley, New York, 1981).
E. C. Titchmarsh, Introduction to the Theory of Fourier Integrals (Oxford Univ. Press, Oxford, 1962).
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Cho, J., Levit, B. Cardinal splines in nonparametric regression. Math. Meth. Stat. 17, 19–34 (2008). https://doi.org/10.3103/S106653070801002X
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S106653070801002X