A Study on the Confidence Region of the Stationary Point in a second Order Response Surface

  • Jorn, Hong S. (Department of Computer Science and Statistics, Seoul National University)
  • Published : 1978.12.01

Abstract

When a response surface by a seconde order polynomial regression model, the stationary point is obtained by solving simultaneous linear equations. But the point is a function of random variables. We can find a confidence region for this point as Box and Hunter provided. However, the confidence region is often too large to be useful for the experiments, and it is necessary to augment additional design points in order to obtain a satisfactory confidence region for the stationary point. In this note, the author suggests a method how to augment design points "eficiently", and shows the change of the confidence region of the estimated stationary point in a response surface.e surface.

Keywords

References

  1. Biometrika v.41 A confidence region for the solution of a set of simultaneous equations with an applications to experimental design Box,G.E.P.;J.S.Hunter
  2. Technometrics v.13 no.3 The augmentation of experimental data to maximize ⅠX'XⅠ Dykstra,O.Jr.
  3. Mimeograph Series No. 936 Computer generated D-optimal, V-optimal and trace optimal maximum bias experimental designs Evans,J.W.
  4. Response Surface Methodology Myers,R.H.