Response surface methodology
In statistics, response surface methodology (RSM) explores the relationships between several explanatory variables and one or more response variables. The method was introduced by G. E. P. Box and K. B. Wilson in 1951. The main idea of RSM is to use a sequence of designed experiments to obtain an optimal response. Box and Wilson suggest using a second-degree polynomial model to do this. They acknowledge that this model is only an approximation, but use it because such a model is easy to estimate and apply, even when little is known about the process.
Basic approach of response surface methodology
An easy way to estimate a first-degree polynomial model is to use a factorial experiment or a fractional factorial design. This is sufficient to determine which explanatory variables have an impact on the response variable(s) of interest. Once it is suspected that only significant explanatory variables are left, then a more complicated design, such as a central composite design can be implemented to estimate a second-degree polynomial model, which is still only an approximation at best. However, the second-degree model can be used to optimize (maximize, minimize, or attain a specific target for). This approach is being used efficiently in optimizing the surface roughness Response.
Cubic designs are discussed by Kiefer, by Atkinson, Donev, and Tobias and by Hardin and Sloane.
Spherical designs are discussed by Kiefer and by Hardin and Sloane.
Simplex geometry and mixture experiments
Mixture experiments are discussed in many books on the design of experiments, and in the response-surface methodology textbooks of Box and Draper and of Atkinson, Donev and Tobias. An extensive discussion and survey appears in the advanced textbook by John Cornell.
Multiple objective functions
Some extensions of response surface methodology deal with the multiple response problem. Multiple response variables create difficulty because what is optimal for one response may not be optimal for other responses. Other extensions are used to reduce variability in a single response while targeting a specific value, or attaining a near maximum or minimum while preventing variability in that response from getting too large.
Response surface methodology uses statistical models, and therefore practitioners need to be aware that even the best statistical model is an approximation to reality. In practice, both the models and the parameter values are unknown, and subject to uncertainty on top of ignorance. Of course, an estimated optimum point need not be optimum in reality, because of the errors of the estimates and of the inadequacies of the model.
Nonetheless, response surface methodology has an effective track-record of helping researchers improve products and services: For example, Box's original response-surface modeling enabled chemical engineers to improve a process that had been stuck at a saddle-point for years. The engineers had not been able to afford to fit a cubic three-level design to estimate a quadratic model, and their biased linear-models estimated the gradient to be zero. Box's design reduced the costs of experimentation so that a quadratic model could be fit, which led to a (long-sought) ascent direction.
- Plackett–Burman design
- Box–Behnken design
- IOSO method based on response-surface methodology
- Optimal designs
- Polynomial regression
- Polynomial and rational function modeling
- Surrogate model
- Probabilistic design
- Box, G. E. P. and Wilson, K.B. (1951) On the Experimental Attainment of Optimum Conditions (with discussion). Journal of the Royal Statistical Society Series B13(1):1–45.
- Improving Almost Anything: Ideas and Essays, Revised Edition (Wiley Series in Probability and Statistics) George E. P. Box
- Box, G. E. P. and Wilson, K.B. (1951) On the Experimental Attainment of Optimum Conditions (with discussion). Journal of the Royal Statistical Society Series B 13(1):1–45.
- Box, G. E. P. and Draper, Norman. 2007. Response Surfaces, Mixtures, and Ridge Analyses, Second Edition [of Empirical Model-Building and Response Surfaces, 1987], Wiley.
- Atkinson, A. C. and Donev, A. N. and Tobias, R. D. (2007). Optimum Experimental Designs, with SAS. Oxford University Press. pp. 511+xvi. ISBN 978-0-19-929660-6.
- Cornell, John (2002). Experiments with Mixtures: Designs, Models, and the Analysis of Mixture Data (third ed.). Wiley. ISBN 0-471-07916-2.
- Goos, Peter (2002). The Optimal Design of Blocked and Split-plot Experiments. Lecture Notes in Statistics 164. Springer.
- Kiefer, Jack Carl. (1985). L. D. Brown et al., ed. Jack Carl Kiefer Collected Papers III Design of Experiments. Springer-Verlag. ISBN 0-387-96004-X.
- R. H. Hardin and N. J. A. Sloane, "A New Approach to the Construction of Optimal Designs", Journal of Statistical Planning and Inference, vol. 37, 1993, pp. 339-369
- R. H. Hardin and N. J. A. Sloane, "Computer-Generated Minimal (and Larger) Response Surface Designs: (I) The Sphere"
- R. H. Hardin and N. J. A. Sloane, "Computer-Generated Minimal (and Larger) Response Surface Designs: (II) The Cube"
- Ghosh, S. and Rao, C. R., ed. (1996). Design and Analysis of Experiments. Handbook of Statistics 13. North-Holland. ISBN 0-444-82061-2.
- Gergonne, J. D. (1974) . "The application of the method of least squares to the interpolation of sequences". Historia Mathematica (Translated by Ralph St. John and S. M. Stigler from the 1815 French ed.) 1 (4): 439–447. doi:10.1016/0315-0860(74)90034-2.
- Stigler, Stephen M. (1974). "Gergonne's 1815 paper on the design and analysis of polynomial regression experiments". Historia Mathematica 1 (4): 431–439. doi:10.1016/0315-0860(74)90033-0.
- Peirce, C. S (1876). "Note on the Theory of the Economy of Research". Coast Survey Report: 197–201. (Appendix No. 14). NOAA PDF Eprint. Reprinted in Collected Papers of Charles Sanders Peirce 7. 1958. paragraphs 139–157, and in Peirce, C. S. (July–August 1967). "Note on the Theory of the Economy of Research". Operations Research 15 (4): 643–648. doi:10.1287/opre.15.4.643. Abstract at JSTOR.
- Smith, Kirstine (1918). "On the Standard Deviations of Adjusted and Interpolated Values of an Observed Polynomial Function and its Constants and the Guidance They Give Towards a Proper Choice of the Distribution of the Observations". Biometrika 12 (1/2): 1–85. JSTOR 2331929.