Comparison of Response Surface Designs in a Spherical Region

The objective of the research is to study and compare response surface designs: Central composite designs (CCD), Box- Behnken designs (BBD), Small composite designs (SCD), Hybrid designs, and Uniform shell designs (USD) over sets of reduced models when the design is in a spherical region for 3 and 4 design variables. The two optimality criteria ( D and G ) are considered which larger values imply a better design. The comparison of design optimality criteria of the response surface designs across the full second order model and sets of reduced models for 3 and 4 factors based on the two criteria are presented.

Authors:

• Boonorm Chomtee
• John J. Borkowski

Keywords:

• design optimality criteria
• reduced models
• response surface design
• spherical design region

References:

[1] Mathworks Inc., Matlab Version 7.1, 2010.
[2] Chipman, H.A., "Baysian variable selection with related predictors,"
The Canadian Journal of Statistics, vol. 24, pp.17-36, 1996.
[3] Borkowski, J.J. and Valeroso, E.S., "Comparison of design optimality
criteria of reduced models for response designs in the hypercube,"
Technometrics, vol. 43, pp. 468-477, 2001.