Comparative study of response surface designs with errors-in-variables model

Abstract

This paper investigates the scaled prediction variances in the errors-in-variables model and compares the performance with those in classic model of response surface designs for three factors. The ordinary least squares estimators of regression coefficients are derived from a second-order response surface model with errors in variables. Three performance criteria are proposed. The first is the difference between the empirical mean of maximum value of scaled prediction variance with errors and the maximum value of scaled prediction variance without errors. The second is the mean squared deviation from the mean of simulated maximum scaled prediction variance with errors. The last performance measure is the mean squared scaled prediction variance change with and without errors. In the simulations, 1 000 random samples were performed following three factors with 20 experimental runs for central composite designs and 15 for Box-Behnken design. The independent variables are coded variables in these designs. Comparative results show that for the low level errors in variables, central composite face-centered design is optimal; otherwise, Box-Behnken design has a relatively better performance.

Keywords

response surface modeling / errors in variables / scaled prediction variance

References

[1] Box G. E. P., Wilson K. B. On the experimental attainment of optimum conditions[J]. Journal of the Royal Statistical Society, Series B, 1951, 13(1): 1-45.

[2] Myers R. H., Montgomery D. C. Response Surface Methodology: Process and Product Optimization Using Designed Experiments[M]. 2002, New York: John Wiley & Sons.

[3] Fuller W. A. Measurement Error Models[M]. 1987, New York: Wiley.

[4] Carroll R. J., Ruppert D., Stefanski L. A. Measurement Error in Nonlinear Models[M]. Monographs on Statistics and Applied Probability, 1995, London: Chapman & Hall.

[5] Lau K., Braslavsky J. H., Agüero J. C., et al. An errors-invariables method for non-stationary data with application to mineral exploration[J]. Automatica, 2009, 45(12): 2971-2976.

[6] Tang S., Wang Yonghe. A parameter estimation program for the error-in-variable model[J]. Ecological Modelling, 2002, 156(2/3): 225-236.

[7] Song Weixing. Model checking in errors-in-variables regression[J]. Journal of Multivariate Analysis, 2008, 99(10): 2406-2443.

[8] Coën A., Racicot F.-É. Capital asset pricing models revisited: Evidence from errors in variables[J]. Economics Letters, 2007, 95(3): 443-450.

[9] Vehkalahti K., Puntanen S., Tarkkonen L. Effects of measurement errors in predictor selection of linear regression model[J]. Computational Statistics & Data Analysis, 2007, 52(2): 1183-1195.

[10] Anderson-Cook C. M., Borror C. M., Montgomery D. C. Response surface design evaluation and comparison [J]. Journal of Statistical Planning and Inference, 2009, 139(2): 629-641.

[11] Anderson-Cook C. M. Design Assessment: What Constitutes a Good Experimental Design?[M]. Encyclopedia of Statistics in Quality and Reliability, 2008, New York: Wiley and Sons.

[12] Ozol-Godfrey A., Anderson-Cook C. M., Montgomery D. C. Fraction of design space plots for examining model robustness[J]. Journal of Quality Technology, 2005, 37(3): 223-235.

[13] Zahran A., Anderson-Cook C. M., Myers R. H. Fraction of design space to assess prediction capability of response surface designs[J]. Journal of Quality Technology, 2003, 35(4): 377-386.

[14] Fuller W. A. Errors-in-Variables Model[M]. 1999, New York: John Wiley & Sons.

[15] Riu J., Rius F. X. Assessing the accuracy of analytical methods using linear regression with errors in both axes [J]. Analytical Chemistry, 1996, 68(11): 1851-1857.