Polynomial representations for response surface modeling

In response surface models the expected response is usually taken to be a low degree polynomial in the design variables that are coded from the factor settings. We argue that an overparameterized polynomial representation of the expected response offers great economy and transparency. As an illustration, we exhibit a constructive path of design improvement relative to the Kiefer design ordering, for polynomial regression up to degree three when the experimental domain is a ball.

[1]  J. S. Hunter,et al.  Multi-Factor Experimental Designs for Exploring Response Surfaces , 1957 .

[2]  W. J. Studden,et al.  Tchebycheff Systems: With Applications in Analysis and Statistics. , 1967 .

[3]  J. Kiefer.  Construction and optimality of generalized Youden designs II , 1975 .

[4]  Z. Galil,et al.  Extrapolation designs and Φp-optimum designs for cubic regression on the q-ball , 1979 .

[5]  Berthold Heiligers,et al.  Admissibility of experimental designs in linear regression with constant term , 1991 .

[6]  F. Pukelsheim,et al.  First and second order rotatability of experimental designs, moment matrices, and information surfaces , 1991 .

[7]  F. Pukelsheim,et al.  Rotatability of variance surfaces and moment matrices , 1993 .

[8]  F. Pukelsheim.  Optimal Design of Experiments , 1993 .

[9]  F. Pukelsheim,et al.  On third order rotatability , 1994 .

[10]  Norbert Gaffke,et al.  Computing optimal approximate invariant designs for cubic regression on multidimensional balls and cubes , 1995 .

[11]  Ching-Shui Cheng,et al.  Complete Class Results for the Moment Matrices of Designs Over Permutation-Invariant Sets , 1995 .

[12]  Norbert Gaffke,et al.  30 Approximate designs for polynomial regression: Invariance, admissibility, and optimality , 1996, Design and analysis of experiments.

[13]  F. Pukelsheim,et al.  On optimal third order rotatable designs , 1996 .

[14]  Norman R. Draper,et al.  Mixture models based on homogeneous polynomials , 1998 .