On weighted design optimality criteria and response surface parameterizations
This paper considers weighted design optimality criteria for polynomial responses surfaces. It is shown that there are some particularly simple parameterizations of the response surface for which weighted optimality criteria are equivalent to A-optimality or weighted A-optimality. This is useful in practice as A-optimality search algorithms are readily available.
Year of publication: |
2001
|
---|---|
Authors: | Butler, Neil A. |
Published in: |
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 51.2001, 1, p. 41-46
|
Publisher: |
Elsevier |
Keywords: | A-optimality ASV-optimality D-optimality Hermite polynomial I-optimality Legendre polynomial Orthogonality V-optimality |
Saved in:
Saved in favorites
Similar items by person
-
Updating the forecast function of ARIMA models and the link with DLMs
Butler, Neil A., (1999)
-
A general method of constructing "E"("s"-super-2)-optimal supersaturated designs
Butler, Neil A., (2001)
-
The peculiar shrinkage properties of partial least squares regression
Butler, Neil A., (2000)
- More ...