Skip to main content
SpringerLink
Log in

Experimental design for estimating the optimum point in a response surface

  • Published:
Acta Applicandae Mathematica Aims and scope Submit manuscript

Abstract

The problem of optimal experimental design for response optimization is considered. The optimal point (control)x * of a response surface is to be determined by estimating the response parametersθ from measurements performed at design pointsx i,i=1,...,N. Classical sequential approaches for choosing thex i's are recalled. A loss function related to the issue of response optimization is used to define control-oriented design criteria. The design policies differ depending on whether least-squares or minimum risk estimation is used to estimateθ. Connections between various criteria suggested in the literature are exhibited. Special attention is given to quadratic model responses. Most approaches presented assume that the response is correctly described by a given parametric function over the region of interest. Possible deterministic departures from this function raise the problem of model robustness, and the literature on the subject is briefly surveyed.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Nelder, J. A. and Mead, R.: A simplex method for function minimization,Computer J. 7 (1965), 308–313.

    Google Scholar 

  2. Kiefer, J. and Wolfowitz, J.: Stochastic estimation of the maximum of a regression function,Ann. Math. Statist. 23 (1952), 462–466.

    Google Scholar 

  3. Polyak, B. T. and Tsypkin Ya. Z.: Pseudogradient adaptation and training algorithms,Autom. Remote Control 34(3), (1973), 377–397. (Translated fromAutom. Telemekh. 3 (1973), 45–68.

    Google Scholar 

  4. Dvoretzky, A.: On stochastic approximation,Proc. 3rd Berkeley Symp. Math. Statist. Probab., vol. 1 (1956), 39–55.

    Google Scholar 

  5. Box, G. E. P. and Wilson, K. B.: On the experimental attainment of optimum conditions (with discussion),J. Royal Statist. Soc. B13(1), (1951), 1–45.

    Google Scholar 

  6. Hill, W. J. and Hunter, W. G.: A review of response surface methodology: a literature survey,Technometrics 8 (1966), 571–590.

    Google Scholar 

  7. Myers, R. H.:Response Surface Methodology, Allyn and Bacon, Boston, 1976.

    Google Scholar 

  8. Montgomery, D. C.:Design and Analysis of Experiments, Wiley, New York, 1976.

    Google Scholar 

  9. Steinberg, D. M.: Model robust response surface designs: scaling two-level factorials,Biometrika 72(3), (1985) 513–526.

    Google Scholar 

  10. Brooks, S. H. and Mickey, R. M.: Optimum estimation of gradient direction in steepest ascent experiments,Biometrics 17 (1961), 48–56.

    Google Scholar 

  11. Scheffé, H.: Experiments with mixtures,J. Royal Statist. Soc. B21 (1958), 344–360.

    Google Scholar 

  12. Galil, Z. and Kiefer, J.: Comparison of simplex designs for quadratic mixture models,Technometrics 19(3), (1977) 445–453.

    Google Scholar 

  13. Box, G. E. P. and Hunter, J. S.: Multi-factor experimental designs for exploring response surfaces,Ann. Math. Statist. 28 (1957), 195–241.

    Google Scholar 

  14. Lindley, D. V.: The choice of variables in multiple regression,J. Royal Statist. Soc. B32 (1968), 31–53.

    Google Scholar 

  15. Brooks, R. J.: Optimal regression design for control in linear regression,Biometrika 64(2), (1977), 319–325.

    Google Scholar 

  16. Verdinelli, I. and Wynn, H. P.: Target attainment and experimental design, a Bayesian approach, in Y. Dodge, V. V. Fedorov and H. P. Wynn (eds),Optimal Design and Analysis of Experiments, North-Holland, Amsterdam, 1988, pp. 319–324.

    Google Scholar 

  17. Goodwin, G. C. and Payne, R. L.:Dynamic System Identification: Experiment Design and Data Analysis, Academic Press, New York, 1977.

    Google Scholar 

  18. Chatterjee, S. K. and Mandal, N. K.: Response surface designs for estimating the optimal point,Calcutta Statist. Assoc. Bull. 30 (1981), 145–169.

    Google Scholar 

  19. Chaloner, K.: Optimal Bayesian design for nonlinear estimation, Technical Report 468, University of Minnesota, 1986.

  20. Buonaccorsi, J. P. and Iyer, H. K.: Optimal designs for ratio of linear combinations in the general linear model,J. Statist. Plann. Inference 13 (1986), 345–356.

    Google Scholar 

  21. Silvey, S. D.:Optimal Design, Chapman and Hall, London, 1980.

    Google Scholar 

  22. Chaloner, K. and Larntz, K.: Optimal Bayesian design applied to logistic regression experiments, Technical Report 483, University of Minnesota, 1986.

  23. Chaloner, K.: An approach to experimental design for generalized linear models, in V. V. Fedorov and H. LÄuter (eds),Model Oriented Data Analysis, Springer, Berlin, 1988, pp. 3–12.

    Google Scholar 

  24. Fedorov, V. V.:Theory of Optimal Experiments, Academic Press, New York, 1972.

    Google Scholar 

  25. Pazman, A.:Foundations of Optimum Experimental Design, D. Reidel, Dordrecht, and Veda, Bratislava, 1986.

    Google Scholar 

  26. Elfving, G.: Optimum allocation in linear regression theory,Ann. Math. Statist. 23 (1952), 255–262.

    Google Scholar 

  27. Studden, W. J.: Elfving's theorem and optimal designs for quadratic loss.Ann. Math. Statist. 42 (1971), 1613–1621.

    Google Scholar 

  28. Silvey, S. D.: Optimal design measures with singular information matrices,Biometrika 65(3), (1978) 553–559.

    Google Scholar 

  29. Atwood, C. L.: Convergent design sequences, for sufficiently regular optimality criteria, II: singular case,Ann. Statist. 8(4), (1980), 894–912.

    Google Scholar 

  30. Fedorov, V. V. and Atkinson, A. C.: The optimum design of experiments in the presence of uncontrolled variability and prior information, in Y. Dodge, V. V. Fedorov and H. P. Wynn (eds),Optimal Design and Analysis of Experiments, North-Holland, Amsterdam, 1988, pp. 327–344.

    Google Scholar 

  31. Walter, E. and Pronzato, L.: Qualitative and quantitative experiment design for phenomenological models survey,Automatica 26(2), (1990), 195–213.

    Google Scholar 

  32. Lindley, D. V.: On a measure of information provided by an experiment,Ann. Math. Statist. 27 (1956), 986–1005.

    Google Scholar 

  33. Mandal, N. K.:D-optimal designs for estimating the optimum point in a quadratic response surface rectangular region,J. Statist. Plann. Inference 23 (1989), 243–252.

    Google Scholar 

  34. Pronzato, L. and Walter, E.: Robust experiment design via stochastic approximation,Math. Biosci. 75 (1985), 103–120.

    Google Scholar 

  35. Walter, E. and Pronzato, L.: How to design experiments that are robust to parameter uncertainty,Preprints 7th IFAC/IFORS Symp. Identification and System Parameter Estimation, York, vol. 1 (1985), 921–926.

    Google Scholar 

  36. Walter, E. and Pronzato, L.: Robust experiment design: between qualitative and quantitative identifiabilities, in E. Walter (ed.),Identifiability of Parametric Models, Pergamon, Oxford, 1987, pp. 104–113.

    Google Scholar 

  37. Pronzato, L. and Walter, E.: Robust experiment design for nonlinear regression models, in V. V. Fedorov and H. LÄuter (eds.),Model Oriented Data Analysis, Springer, Berlin, 1988, pp. 77–86.

    Google Scholar 

  38. Pronzato, L. and Walter, E.: Robust experiment design via maximin optimization,Math. Biosci. 89 (1988), 161–176.

    Google Scholar 

  39. Pronzato, L. and Walter, E.: Nonsequential Bayesian experimental design for response optimization, in V. Fedorov, W. G. Müller and I. N. Vuchkov (eds),Proc. 2nd Internat. Workshop on ModelOriented Data Analysis, St. Kyrik, Bulgaria, Physica-Verlag, Heidelberg, 1992, pp. 89–102.

    Google Scholar 

  40. Pilz, J.:Bayesian Estimation and Experimental Design in Linear Regression Models, Teubner Texte zur Mathematik, Leipzig, 1983.

    Google Scholar 

  41. Bandemer, H., NÄttier, W. and Pilz, J.: Once more: Optimal experimental design for regression models (with discussion),Statistics 18(2), (1987), 171–217.

    Google Scholar 

  42. Giovagnoli, A. and Verdinelli, I.: BayesD-optimal andE-optimal block designs,Biometrika 70(3) (1983), 695–706.

    Google Scholar 

  43. Chaloner, K.: Optimal Bayesian experimental design for linear models,Ann. Statist. 12(1) (1984), 283–300.

    Google Scholar 

  44. Ylvisaker, D.: Prediction and design,Ann. Statist. 15(1) (1987), 1–19.

    Google Scholar 

  45. Steinberg, D. M. and Hunter, W. G.: Experimental design: review and comment (with discussion),Technometrics 26(2) (1984), 71–130.

    Google Scholar 

  46. Box, G. E. P. and Draper, N. R.: A basis for the selection of a response surface design,J. Amer. Statist. Assoc. 54 (1959), 622–654.

    Google Scholar 

  47. Karson, M. J., Manson, A. R. and Hader, R. J.: Minimum bias estimation and experimental design for response surfaces,Technometrics 11 (1969), 461–475.

    Google Scholar 

  48. Kiefer, J.: Optimum designs for fitting biased multiresponse surfaces, in P. R. Krishnaiah (ed.),Maltivariate Analysis 3, Academic Press, New York, 1973, pp. 287–297.

    Google Scholar 

  49. Stigler, S. M.: Optimal experimental design for polynomial regression,J. Amer. Statist. Assoc. 66 (1971), 311–318.

    Google Scholar 

  50. Studden, W. J.: Some robust-typeD-optimal designs in polynomial regression,J. Amer. Statist. Assoc. 77 (1982), 916–921.

    Google Scholar 

  51. Huber, P. J.: Robustness and designs, in J. N. Srivastava (ed.),A Survey of Statistical Design and Linear Models, North-Holland, Amsterdam, 1975, pp. 287–301.

    Google Scholar 

  52. Marcus, M. B. and Sacks, J.: Robust designs for regression problems, inStatistical Decision Theory and Related Topics II, Academic Press, New York, 1977, pp. 245–268.

    Google Scholar 

  53. Sacks, J. and Ylvisaker, D.: Linear estimation for approximately linear models,Ann. Statist. 6(5) (1978), 1122–1137.

    Google Scholar 

  54. Sacks, J. and Ylvisaker, D.: Some model robust designs in regression,Ann. Statist. 12(4) (1984), 1324–1348.

    Google Scholar 

  55. Pesotchinsky, L.: Optimal robust designs: linear regression in 67-01,Ann. Statist. 10(2) (1982), 511–525.

    Google Scholar 

  56. Welch, W. J.: A mean squared error criterion for the design of experiments,Biometrika 70(1) (1983), 205–213.

    Google Scholar 

  57. Kiefer, J.: General equivalence theory for optimum designs (approximate theory).Ann. Statist. 2(5) (1974), 849–879.

    Google Scholar 

  58. O'Hagan, A.: Curve fitting and optimal design for prediction (with discussion),J. Royal Statist. Soc. B40(1) (1978), 1–42.

    Google Scholar 

  59. Goldstein, M.: The linear Bayes regression estimator under weak prior assumptions,Biometrika 67(3) (1980), 621–628.

    Google Scholar 

  60. Blight, B. J. N. and Ott, L.: A Bayesian approach to model inadequacy for polynomial regression,Biometrika 62(1) (1975), 79–88.

    Google Scholar 

  61. Sacks, J. and Ylvisaker, D.: Model robust design in regression: Bayes theory, in L. M. Le Cam and R. A. Olshen (eds),Proc. Berkeley Conference in Honour of J. Neyman and J. Kiefer, vol.2, 1985, pp. 667–679.

  62. Currin, C., Mitchell, T., Morris, M. and Ylvisaker D.: A Bayesian approach to the design and analysis of computer experiments, ORNL Technical Report 6498, available from the National Technical Information Service, 5285 Port Royal Road, Springfield, VA 22161, 1988.

  63. Sacks, J., Welch, W.J., Mitchell, T. and Wynn, H. P.: Design and analysis of computer experiments (with discussion),Statist. Sci. 4(4) (1989), 409–435.

    Google Scholar 

  64. Shewry, M. C. and Wynn, H. P.: Maximum entropy sampling,J. Appl. Statist. 14 (1987), 165–170.

    Google Scholar 

  65. Sacks, J., Schiller, S. B. and Welch, W. J.: Designs for computer experiments,Technometrics 31 (1989), 41–47.

    Google Scholar 

  66. Atkinson, A. C. and Donev, A. N.: Algorithms, exact design and blocking in response surface and mixture designs, in Y. Dodge, V. V. Fedorov and H. P. Wynn (eds),Optimal Design and Analysis of Experiments, North-Holland, Amsterdam, 1988, pp. 61–69.

    Google Scholar 

  67. Yonchev, H.: New computer procedures for constructingD-optimal designs, in Y. Dodge, V.V. Fedorov and H. P. Wynn (eds),Optimal Design and Analysis of Experiments, North-Holland, Amsterdam, 1988, pp. 71–80.

    Google Scholar 

  68. Atkinson, A. C. and Cox, D. R.: Planning experiments for discriminating between models (with discussion),J. Royal Statist. Soc. B36 (1974), 321–348.

    Google Scholar 

  69. Hill, P. D. H.: A review of experimental design procedures for regression model discrimination,Technometrics 20(1) (1978), 15–21.

    Google Scholar 

  70. Ford, I. and Silvey, S. D.: A sequentially constructed design for estimating a nonlinear parametric function,Biometrika 67(2) (1980), 381–388.

    Google Scholar 

  71. Wu, C. F. J.: Asymptotic inference from sequential design in a nonlinear situation,Biometrika 72(3) (1985), 553–558.

    Google Scholar 

  72. Ford, I., Titterington, D. M. and Wu, C. F. J.: Inference and sequential design,Biometrika 72(3) (1985), 545–551.

    Google Scholar 

  73. Zacks, S.: Problems and approaches in design of experiments for estimation and testing in nonlinear models, in P. R. Krishnaiah (ed.),Multivariate Analysis IV, North-Holland, Amsterdam, 1977, pp. 209–223.

    Google Scholar 

  74. Bayard, D. S. and Schumitzky, A.: A stochastic control approach to optimal sampling design, Univ. of Southern California, School of Medicine, Lab. of Applied Pharmacokinetics, Technical Report,90-1 (1990).

  75. Chernoff, H.: Approaches in sequential design of experiments, in J. N. Srivastava (ed.),A Survey of Statistical Design and Linear Models, North-Holland, Amsterdam, 1975, pp. 67–90.

    Google Scholar 

  76. Fel'dbaum, A. A.:Optimal Control Systems, Academic Press, New York, 1965.

    Google Scholar 

  77. Bar-Shalom, Y. and Tse, E.: Dual effect, certainty equivalence, and separation in stochastic control,IEEE Trans. Automat. Control AC-19(5) (1974), 494–500.

    Google Scholar 

  78. Padilla, C. S. and Cruz, JR. J. B.: A linear dynamic feedback controller for stochastic systems with unknown parameters,IEEE Trans. Automat. Control AC-22(1) (1977), 50–55.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Laboratoire I3S, CNRS-URA 1376, 250 rue Albert Einstein, 06560, Sophia-Antipolis, Valbonne, France

    Luc Pronzato

  2. Laboratoire des Signaux et Systèmes, CNRS/Ecole Supérieure d'Electricité Plateau de Moulon, 1192, Gif-sur-Yvette Cedex, France

    Eric Walter

Authors
  1. Luc Pronzato
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Eric Walter
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Pronzato, L., Walter, E. Experimental design for estimating the optimum point in a response surface. Acta Appl Math 33, 45–68 (1993). https://doi.org/10.1007/BF00995494

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00995494

Mathematics Subject Classifications (1991)

Key words

Search

Navigation