Integer-Valued, Minimax Robust Designs for Estimation and Extrapolation in Heteroscedastic, Approximately Linear Models

Abstract We present our findings on a new approach to robust regression design. This approach differs from previous investigations into this area in three respects: The use of a finite design space, the use of simulated annealing to carry out the numerical minimization problems, and in our search for integer-valued, rather than continuous, designs. We present designs for the situation in which the response is thought to be approximately polynomial. We also discuss the cases of approximate first- and second-order multiple regression. In each case we allow for possible heteroscedasticity and also obtain minimax regression weights. The results are extended to cover extrapolation of the regression response to regions outside of the design space. A case study involving dose-response experimentation is undertaken. The optimal robust designs, which protect against bias as well as variance, can be roughly described as being obtained from the classical variance-minimizing designs by replacing replicates with clusters of observations at nearby but distinct sites.

[1]  D. Wiens,et al.  Robust extrapolation designs and weights for biased regression models with heteroscedastic errors , 1999 .

[2]  D. Wiens.  Minimax Robust Designs and Weights for Approximately Specified Regression Models With Heteroscedastic Errors , 1998 .

[3]  H. Dette,et al.  Robust optimal extrapolation designs , 1996 .

[4]  F. Pukelsheim.  Optimal Design of Experiments , 1993 .

[5]  F. Pukelsheim,et al.  Efficient rounding of approximate designs , 1992 .

[6]  Douglas P. Wiens,et al.  Minimax designs for approximately linear regression , 1992 .

[7]  Douglas P. Wiens,et al.  Robust minimax designs for multiple linear regression , 1990 .

[8]  R. K. Meyer,et al.  Constructing exact D-optimal experimental designs by simulated annealing , 1988 .

[9]  W. J. Studden,et al.  Model robust extrapolation designs , 1988 .

[10]  L. Haines.  The application of the annealing algorithm to the construction of exact optimal designs for linear-regression models , 1987 .

[11]  W. Press,et al.  Numerical recipes in C. The art of scientific computing , 1987 .

[12]  M. E. Johnson,et al.  Generalized simulated annealing for function optimization , 1986 .

[13]  William H. Press,et al.  Numerical recipes in C. The art of scientific computing , 1987 .

[14]  M. C. Spruill.  Optimal designs for minimax extrapolation , 1984 .

[15]  Ker-Chau Li,et al.  Robust Regression Designs when the Design Space Consists of Finitely Many Points , 1984 .

[16]  L. Pesotchinsky,et al.  Optimal Robust Designs: Linear Regression in $R^k$ , 1982 .

[17]  W. Notz,et al.  Robust designs for nearly linear regression , 1982 .

[18]  R. Jennrich,et al.  Optimal designs for dose response experiments in cancer research , 1979 .

[19]  J. Cornfield,et al.  Carcinogenic risk assessment. , 1977, Science.

[20]  H. Guess,et al.  Uncertainty estimates for low-dose-rate extrapolations of animal carcinogenicity data. , 1977, Cancer research.

[21]  W. J. Studden.  OPTIMAL DESIGNS FOR INTEGRATED VARIANCE IN POLYNOMIAL REGRESSION , 1977 .

[22]  Agnes M. Herzberg,et al.  Some Designs for Extrapolation Outside a Sphere , 1973 .

[23]  W. J. Studden,et al.  Theory Of Optimal Experiments , 1972 .

[24]  W. J. Studden.  Optimal Designs for Multivariate Polynomial Extrapolation , 1971 .

[25]  J. Kiefer,et al.  THE ROLE OF SYMMETRY AND APPROXIMATION IN EXACT DESIGN OPTIMALITY , 1971 .

[26]  P. Hoel,et al.  Optimal Spacing and Weighting in Polynomial Prediction , 1964 .

[27]  Jacob Wolfowitz,et al.  Optimum extrapolation and interpolation designs, I , 1964 .

[28]  G. Box,et al.  A Basis for the Selection of a Response Surface Design , 1959 .