Interpolating Spline Methods for Density Estimation I. Equi-Spaced Knots.

Abstract

Statistical properties of the histospline density estimate of Boneva-Kendall-Stefanov-Schoenberg are found. This density estimate is the derivative of a cubic spline of interpolation to the sample cumulative distribution at equally spaced points. The spacing of these points is chosen in an optimal manner. The boundary values of the spline are estimated from the data. It is shown that the mean square convergence rate of this density estimate at a point achieves the best obtainable rate. (Author)

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 1973
Accession Number
AD0770962

Entities

People

  • Grace Wahba

Organizations

  • University of Wisconsin–Madison

Tags

DTIC Thesaurus Topics

  • Boundaries
  • Convergence
  • Interpolation
  • Mathematical Analysis

Fields of Study

  • Mathematics

Readers

  • Approximation Theory.

Technology Areas

  • Space