Exact D-optimal designs for polynomial regression without intercept

For the regression model fk(x)=(x,x2,...,xk)T on [a,1], -1[less-than-or-equals, slant]a<1, the exact n-point D-optimal designs are proved to be ones that put mass as equally as possible among the support points of the approximate D-optimal design for fk(x) if n[greater-or-equal, slanted]k, a=-1 and k=2,4, if and k=2, and if and k=3. For the other cases, the properties of exact D-optimal designs are discussed on the basis of an intensive numerical study.

MoreLess

Year of publication:	1999
Authors:	Chang, Fu-Chuen
Published in:	Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 44.1999, 2, p. 131-136
Publisher:	Elsevier
Keywords:	Approximate and exact design D-optimal Gaffke's condition Polynomial regression without intercept Salaevskii's conjecture

More details

Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10005223830