Confidence intervals and an improved ridge analysis of response surfaces

作者: Raymond H Myers , Eleanor D Cambpell , Jr. Carter Walter H , Vernon M Chinchilli

DOI: 10.1080/00401706.1986.10488152

关键词:

摘要: The user of RSM techniques gains considerable insight into the nature stationary point and underlying response surface from estimates eigenvalues matrix pure mixed quadratic regression coefftcients, B. This article presents illustrates methodology for constructing conservative confidence limits on this as well mean at a constrained optimum. When interval about an eigenvalue B includes zero, change in strategy analysis is required; one suggested illustrated.

参考文章(16)
Norman R. Draper, "RIDGE ANALYSIS" OF RESPONSE SURFACES Technometrics. ,vol. 5, pp. 469- 479 ,(1963) , 10.1080/00401706.1963.10490125
Emil Spjotvoll, MULTIPLE COMPARISON OF REGRESSION FUNCTIONS. Annals of Mathematical Statistics. ,vol. 43, pp. 1076- 1088 ,(1972) , 10.1214/AOMS/1177692461
William G. Hunter, William J. Hill, A Review of Response Surface Methodology: A Literature Survey* Technometrics. ,vol. 8, pp. 571- 590 ,(1966) , 10.1080/00401706.1966.10490404
Donald M. Stablein, Walter H. Carter, Galen L. Wampler, Confidence regions for constrained optima in response-surface experiments. Biometrics. ,vol. 39, pp. 759- 763 ,(1983) , 10.2307/2531105
H. C. Hamaker, O. L. Davies, F. J. van Dun En, The design and analysis of industrial experiments ,(1954)
G. E. P. Box, K. B. Wilson, On the Experimental Attainment of Optimum Conditions Springer Series in Statistics. ,vol. 13, pp. 270- 310 ,(1992) , 10.1007/978-1-4612-4380-9_23
William G. Madow, T. W. Anderson, Introduction to Multivariate Statistical Analysis. American Mathematical Monthly. ,vol. 66, pp. 432- ,(1959) , 10.2307/2308777