Universal Consistency of Partitioning-Estimates of a Regression Function for Randomly Missing Data

  • A. Carbonez
  • L. Györfi
  • E. C. van der Meulen
Conference paper

Abstract

The weak and strong universal consistencies of partitioning estimates of a regression function are shown for incomplete sample. Here incomplete sample means that some sample points are missing according to a random missing mechanism operated on the observation vectors.

Keywords

Entropy 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Beran, R. (1981). Nonparametric regression with randomly censored survival data. Technical Report, Univ. California, Berkeley.Google Scholar
  2. [2]
    Dabrowska, D.M. (1987). Nonparametric regression with censored survival data. Scandinavian Journal of Statistics 14, 181–197.Google Scholar
  3. [3]
    Devroye, L. (1987). A Course in Density Estimation. Birkhauser, Boston.Google Scholar
  4. [4]
    Devroye, L. and Györfi, L. (1985). Distribution free exponential bound for the L1 error of partitioning-estimates of a regression function. Probability and Statistical Decision Theory (Ed. G. Konecny, F. Mogyoródi, W. Wertz) D. Reidel, Dordrecht, 67–76.Google Scholar
  5. [5]
    Gonzalez-Manteiga, W. and Cadarso-Suarez, C.M. (1991). Linear regression with randomly right-censored data using prior nonparametric estimation. In Nonparametric Functional Estimation and Related Topics (Ed. Roussas, G.) Kluwer Academic Publisher, 315-328.Google Scholar
  6. [6]
    Györfi, L. (1991). Universal consistencies of a regression estimate for unbounded regression functions. In Nonparametric Functional Estimation and Related Topics (Ed. Roussas, G.) Kluwer Academic Publisher, 329-338.Google Scholar
  7. [7]
    Györfi, L. and van der Meulen, E.C. (1987). Density free convergence properties of various estimators of entropy. Computational Statistics and Data Analysis 5, 425–436.CrossRefGoogle Scholar
  8. [8]
    Stone, C.J. (1977). Consistent nonparametric regression. Annals of Statistics 5, 595–645.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • A. Carbonez
    • 1
    • 2
  • L. Györfi
    • 1
    • 2
  • E. C. van der Meulen
    • 1
    • 2
  1. 1.Department of MathematicsKatholieke Universiteit LeuvenHeverleeBelgium
  2. 2.Hungarian Academy of SciencesTechnical University of BudapestBudapestHungary

Personalised recommendations