Orthogonal series regression estimators for an irregularly spaced design
Volume 27 / 2000
Applicationes Mathematicae 27 (2000), 309-318
DOI: 10.4064/am-27-3-309-318
Abstract
Nonparametric orthogonal series regression function estimation is investigated in the case of a fixed point design where the observation points are irregularly spaced in a finite interval [a,b]i ⊂ ℝ. Convergence rates for the integrated mean-square error and pointwise mean-square error are obtained in the case of estimators constructed using the Legendre polynomials and Haar functions for regression functions satisfying the Lipschitz condition.
