×

Some response surface designs for finding optimal conditions. (English) Zbl 0692.62062

Summary: This paper deals with the use of the notion of \(D_ s\)-optimality for certain response surface designs. Previous work indicates that for detection of the nature of the response surface system and for the computation of optimum conditions, estimation of second order terms is very important. As a result, \(D_ s\)-optimality is a natural approach.
The central composite design, two variable equiradial design and the Box- Behnken design are the subjects of the study. Designs are tabulated for the case of \(D_ s\) and D-optimality. For the central composite design ‘weights’ are established which are associated with factorial, star, and center points. These weights are to be applied in cases where the user has the capability to replicate the design points.

MSC:

62K05 Optimal statistical designs
62K99 Design of statistical experiments
62Q05 Statistical tables
Full Text: DOI

References:

[1] Atkinson, A. C., The design of experiments to estimate the slope of a response surface, Biometrika, 57, 319-328 (1970) · Zbl 0196.22201
[2] Box, G. E.P., Choice of response surface design and alphabetic optimality, Utilitas Math., 21B, 11-55 (1982) · Zbl 0524.62073
[3] Box, G. E.P.; Behnken, D. W., Some new three-level designs for the study of quantitative variables, Technometrics, 2, 455-475 (1960) · Zbl 0103.12003
[4] Box, G. E.P.; Draper, N. R., Empirical Model-Building and Response Surfaces (1987), Wiley: Wiley New York · Zbl 0482.62065
[5] Box, G. E.P.; Hunter, J. S., Multifactor experimental designs for exploring response surfaces, Ann. Math. Statist., 28, 195-241 (1957) · Zbl 0080.35901
[6] Box, G. E.P.; Wilson, K. B., On the experimental attainment of optimum conditions, J. Roy. Statist. Soc. Ser. B, 13, 1-45 (1951) · Zbl 0043.34402
[7] Technometrics, 15, 430 (1973), Corrigendum · Zbl 0258.62045
[8] Carter, W. H.; Chinchilli, V. M.; Myers, R. H.; Campbell, E. D., Confidence intervals and an improved ridge analysis of response surfaces, Technometrics, 28, 339-346 (1986) · Zbl 0614.62038
[9] Chatterjee, S. K.; Mandel, N. K., Response surface designs for estimating the optimum point, Calcutta Statist. Assoc. Bull., 30, 145-151 (1981) · Zbl 0525.62071
[10] Davies, O. L., The Design and Analysis of Industrial Experiments (1954), Hafner: Hafner New York
[11] Draper, N. R., Third order rotatable designs in three dimensions, Ann. Math. Statist., 31, 865-872 (1960) · Zbl 0103.12004
[12] Draper, N. R., Third order rotatable designs in three dimensions: Some specific designs, Ann. Math. Statist., 32, 910-913 (1961) · Zbl 0100.14404
[13] Draper, N. R., Third order rotatable designs in three factors: Analysis, Technometrics, 4, 219-234 (1962) · Zbl 0113.13303
[14] Draper, N. R., Ridge analysis of response surfaces, Technometrics, 24, 127-133 (1963) · Zbl 0485.62075
[15] Draper, N. R., Center points in second order response surface designs, Technometrics, 24, 127-133 (1982) · Zbl 0485.62075
[16] Farrell, R. H.; Kiefer, J.; Walbran, A., Optimum multivariate designs, Fifth Berkeley Symposium, 113-138 (1967) · Zbl 0193.17101
[17] Galil, Z.; Kiefer, J., Comparison of rotatable designs for regression on balls, I (Quadratic), J. Statist. Plann. Inference, 1, 27-40 (1977) · Zbl 0394.62058
[18] Hill, W. J.; Hunter, W. G., Design of experiments for subsets of parameters, Technometrics, 16, 425-434 (1974) · Zbl 0311.62045
[19] Hoerl, A. E., Optimum solution of many variable equations, Chemical Engineering Progress, 55, 69-78 (1959)
[20] Hoke, A. T., Economical second order designs based on irregular fractions of the \(3^n\) factorial, Technometrics, 17, 375-384 (1974) · Zbl 0285.62052
[21] Karlin, S.; Studden, W. J., Optimal experimental designs, Ann. Math. Statist., 37, 783-815 (1965) · Zbl 0151.23904
[22] Khuri, A. I.; Cornell, J. A., Response Surfaces (1987), Marcel Dekker: Marcel Dekker New York · Zbl 0632.62069
[23] Kiefer, J., Optimal designs in regression problems, II, Ann. Math. Statist., 32, 298-325 (1961) · Zbl 0099.13502
[24] Kiefer, J.; Wolfowitz, J., Optimum designs in regression problems, Ann. Math. Statist., 30, 271-294 (1959) · Zbl 0090.11404
[25] Kiefer, J.; Wolfowitz, J., The equivalence of two extremum problems, Canad. J. Math., 12, 363-366 (1960) · Zbl 0093.15602
[26] Lim, Y. B.; Studden, W. J., Designs for multivariate polynomial regression on the \(q\)-cube, Ann. Statist., 16, 3, 1225-1240 (1988) · Zbl 0664.62075
[27] Lucas, J. M., Optimum composite designs, Technometrics, 16, 561-567 (1974) · Zbl 0294.62099
[28] Lucas, J. M., Which response surface design is best, Technometrics, 18, 411-417 (1976) · Zbl 0342.62051
[29] Lucas, J. M., Design efficiencies for varying numbers of centre points, Biometrika, 64, 145-147 (1977) · Zbl 0347.62058
[30] Myers, R. H., Response Surface Methodology (1976), Department of Statistics, Virginia Polytechnic Institute and State University: Department of Statistics, Virginia Polytechnic Institute and State University Blacksburg, VA
[31] Myers, R. H.; Lahoda, S. J., A generalization of the response surface mean square error criterion with a specific application to the slope, Technometrics, 17, 481-486 (1975) · Zbl 0331.62051
[32] Ott, L.; Mendenhall, W., Designs for estimating the slope of a second order linear model, Technometrics, 14, 341-353 (1972) · Zbl 0235.62016
[33] Pesotchinsky, L., D-optimum and quasi-D-optimum second-order designs on a cube, Biometrika, 62, 335-340 (1975) · Zbl 0309.62054
[34] St. John, R. C.; Draper, N. R., D-optimality for regression designs: A review, Technometrics, 17, 15-23 (1975) · Zbl 0295.62081
[35] Steinberg, D. M.; Hunter, W. G., Experimental design: Review and comment, Technometrics, 26, 71-97 (1984) · Zbl 0549.62048
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.