The Annals of Statistics

Efficient $D_s$-Optimal Designs for Multivariate Polynomial Regression on the $q$-Cube

Yong B. Lim and W. J. Studden

Full-text: Open access

Abstract

Polynomial regression in $q$ variables of degree $n$ on the $q$-cube is considered. Approximate $D$-optimal and approximate $D_s$-optimal designs for estimating higher degree terms are investigated. Numerical results are given for $n = 2$ with arbitrary $q$ and for $n = 3, 4, 5$ and $q = 2, 3$. Exact solutions are given within the class of product designs together with some efficiency calculations.

Article information

Source
Ann. Statist., Volume 16, Number 3 (1988), 1225-1240.

Dates
First available in Project Euclid: 12 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1176350957

Digital Object Identifier
doi:10.1214/aos/1176350957

Mathematical Reviews number (MathSciNet)
MR959198

Zentralblatt MATH identifier
0664.62075

JSTOR
links.jstor.org

Subjects
Primary: 62K05: Optimal designs
Secondary: 62J05: Linear regression

Keywords
$D_s$-optimal designs symmetric designs product designs polynomial regression on the $q$-cube canonical moments

Citation

Lim, Yong B.; Studden, W. J. Efficient $D_s$-Optimal Designs for Multivariate Polynomial Regression on the $q$-Cube. Ann. Statist. 16 (1988), no. 3, 1225--1240. doi:10.1214/aos/1176350957. https://projecteuclid.org/euclid.aos/1176350957


Export citation