ERROR INFERENCE FOR NONPARAMETRIC REGRESSION

B. RUTHERFORD1 AND S. YAKOWITZ2

1 The Reliability Department, Sandia Laboratories, Albuquerque, NM 87112, U.S.A.
2 Systems and Industrial Engineering Department, University of Arizona,
Tucson, AZ 85721, U.S.A.

(Received August 29, 1988; revised October 2, 1989)

Abstract.    This study examines means for inferring the distribution of the error in nonparametric regression. The central objective is to develop confidence intervals for nonparametric regression. Our computational study would seem to affirm that our methods are potentially useful in cases of small sample size or heterogeneously distributed error. Theoretical developments offer sufficient conditions for asymptotic normality.

Key words and phrases:    Confidence intervals, bootstrapping, asymptotic normality, error inference.

Source ( TeX , DVI , PS )