Analyzing optima in the exploration of multiple response surfaces.

A method is presented for testing the equality of some or all (constrained or unconstrained) optima in a response surface analysis. An estimator of a common location of stationary points is obtained by a standard multivariate testing procedure and a confidence region associated with the common optimum is derived. The procedure is illustrated by the estimation of a common optimum in a multiple response experiment. The multivariate approach facilitates a more efficient estimation of the optimum than the usual univariate response surface analysis and provides additional tests of the response surface model.

[1]  G. Derringer,et al.  Simultaneous Optimization of Several Response Variables , 1980 .

[2]  D. A. Williams,et al.  An exact confidence interval for the relative potency estimated from a multivariate bioassay , 1988 .

[3]  A. Khuri,et al.  Simultaneous Optimization of Multiple Responses Represented by Polynomial Regression Functions , 1981 .

[4]  G. R. Dolby Generalized Least Squares and Maximum Likelihood Estimation of Non‐Linear Functional Relationships , 1972 .

[5]  Point and interval estimation in the combination of bioassay results. , 1976, The Journal of hygiene.

[6]  George E. P. Box,et al.  A CONFIDENCE REGION FOR THE SOLUTION OF A SET OF SIMULTANEOUS EQUATIONS WITH AN APPLICATION TO EXPERIMENTAL DESIGN , 1954 .

[7]  R. H. Myers,et al.  Response Surface Techniques for Dual Response Systems , 1973 .

[8]  E D Campbell,et al.  Drug activity and therapeutic synergism in cancer treatment. , 1982, Cancer research.

[9]  G. R. Dolby,et al.  Functional relationships having many independent variables and errors with multivariate normal distribution , 1975 .

[10]  Maximo C. Gacula,et al.  Statistical Methods in Food and Consumer Research , 1985 .

[11]  Norman R. Draper,et al.  "RIDGE ANALYSIS" OF RESPONSE SURFACES , 1963 .

[12]  W. H. Carter,et al.  Confidence regions for constrained optima in response-surface experiments. , 1983, Biometrics.

[13]  J. Pollard A HANDBOOK OF Numerical and statistical techniques: Point and interval estimation , 1977 .

[14]  Raymond H. Myers,et al.  Confidence intervals and an improved ridge analysis of response surfaces , 1986 .

[15]  E. M. Carter,et al.  Analysis of parallel-line assays with multivariate responses , 1985 .