D-optimal designs for polynomial regression with exponential weight function

Weighted polynomial regression with exponential weight function on an interval is considered. The D -optimal designs are completely characterized via three differential equations. Some invariant properties of the optimal designs under affine transformation are derived. The optimal design as degree o...

Full description

Saved in:
Bibliographic Details
Published in:Metrika 2009-11, Vol.70 (3), p.339-354
Main Authors: Chang, Fu-Chuen, Chang, Hsiu-Ching, Wang, Sheng-Shian
Format: Article
Language:English
Subjects:
Economic Theory/Quantitative Economics/Mathematical Methods
Mathematics and Statistics
Probability Theory and Stochastic Processes
Statistics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Weighted polynomial regression with exponential weight function on an interval is considered. The D -optimal designs are completely characterized via three differential equations. Some invariant properties of the optimal designs under affine transformation are derived. The optimal design as degree of polynomial goes to infinity, is shown to converge weakly to the arcsin distribution. Comparisons of the optimal designs with the arcsin distribution are also made.
ISSN:0026-1335
1435-926X
DOI:10.1007/s00184-008-0195-2