Exact Constrained Optimal Design


  • 김영일 (중앙대학교 정보시스템학과)
  • Published : 2009.03.30


It is very rare to conduct an experimental design with a single objective in mind. since we have uncertainties in model and its assumptions. Basically we have three approaches in literature to handle this problem, the mini-max, compound, constrained experimental design. Since Cook and Wong (1994) announced the equivalence between the compound and the constrained design, many constrained experimental design approaches have adopted the approximate design algorithm of compound experimental design. In this paper we attempt to modify the row-exchange algorithm under exact experimental design setting, not approximate experimental design one. This attempt will provide more realistic design setting for the field experiment. In this process we proposed another criterion on how to set the constrained experimental design. A graph to show the general issue of infeasibility, which occurs quite often in constrained experimental design, is suggested.


  1. Box, G. E .P. and Draper, N. R. (1975). Robust design, Biometrika, 62, 347-352
  2. Cook, R. D. and Fedorov, V. V. (1995). Constrained optimization of experimental design, Statistics, 26, 129-178
  3. Cook, R. D. and Nachtsheim, C. J. (1980). A comparison of algorithms for constructing exact D-optimal designs, Technometrics, 22, 315-324
  4. Cook, R. D. and Wong, W. K. (1994). On the equivalence of constrained and compound optimal designs, Journal of the American Statistical Association, 89, 687-692
  5. Fedorov, V. V. (1972). Theory of Optimal Experiments, Academic Press, New York
  6. Gaffke, N. and Krafft, O. (1982). Exact D-optimum designs for quadratic regression, Journal of Royal Statistical Society, Series B, 44, 394-397
  7. Huang, Y. C. and Wong, W. K. (1998). Sequential construction of multiple-objective optimal designs, Biometrics, 54, 1388-1397
  8. Johnson, M. E. and Nachtsheim, C. J. (1983). Some guidelines for constructing exact D-optimal designs on convex design spaces, Technometrics, 25, 271-277
  9. Kahng, M. W. and Kim, Y. I. (2002). Multiple constrained optimal experimental design, The Korean Communications in Statistics, 9, 619-627
  10. Kiefer, J. (1971). The Role of Symmetry and Approximation in Exact Design Optimality, In Statistical Decision Theory and Related Topics, Academic Press, New York
  11. Kiefer, J. (1974). General equivalence theory for optimal designs (approximate theory), The Annals of Statistics, 2, 849-879
  12. Kim, Y. and Lim, Y. B. (2007). Hybrid approach when multiple objectives exist, The Korean Communica-tions in Statistics, 14, 531-540
  13. Lauter, E. (1974). Experimental planning in a class of models, Mathematische Operationsforschung und Statistik, 5, 673-708
  14. Lee, C. M. S. (1987). Constrained optimal designs for regression models, Communications in Statistics, Part A- Theory and Methods, 16, 765-783
  15. Lim, Y. B. (1991). Exact $D_{\delta}$-efficient designs for quadratic response surface model, Journal of the Korean Statistical Society, 20, 156-161
  16. Meyer, R. K. and Nachtsheim, C. J. (1995). The coordinate-exchange algorithm for constructing exact optimal experimental designs, Technometrics, 37, 60-69
  17. Mikulecka, J. (1983). On hybrid experimental designs, Kybernetika, 19, 1-14
  18. Mitchell, T. J. (1974). An algorithm for the construction of D-optimal experimental designs, Technometrics, 16, 203-210
  19. Pesotchinsky, L. L. (1975). D-optimum and quasi-D-optimum second order designs on a cube, Biometrika, 62, 335-340
  20. Stigler, S. M. (1971). Optimal experimental design for polynomial regression, Journal of the American Statistical Association, 66, 311-318
  21. Wynn, H. P. (1972). Results in the theory and construction of D-optimum experimental designs, Journal of Royal Statistical Society, Series B, 34, 133-147