The Construction of Trend-Free Experimental Plans on Two-Level Split-Plot Designs
In most experimental designs, the standard procedure involves randomization of the factor level combination run order. There are cases, however, where it is known that a time or position trend that can seriously compromise the results of the experiment may be present. These trends include wear of tooling and equipment, learning curves, change in temperatures, etc; and may show up as linear, quadratic or even higher order trends. All previously published work [2-9] has dealt with various methods of constructing trend-resistant run order plans on full and fractional factorial designs. The objective of this work is to establish the foundations of a generalized method for constructing linear and quadratic trend-resistant plans in two-level split-plot designs that addresses all dimensions along which these trends may occur. The methodology involves development of a hybrid approach combining the Foldover Method and the Daniel and Wilcoxon (D-W) Method in each of the dimensions of interest and embedding these in a non-linear integer programming model in the search for a feasible solution. Feasibility of this approach is shown for the particular case of a split-plot design (2^sup 5^ whole-plot factors and 3^sup 1^ × 2^sup 1^ split-plot factors) performed on abrasive machining. In this case study, an experimental plan that is robust against all linear trends and most quadratic trends was achieved.
Proceedings of the Industrial Engineering Research Conference, IERC 2004
Carrano, Andres L. and Thorn, Brian K., "The Construction of Trend-Free Experimental Plans on Two-Level Split-Plot Designs" (2004). Engineering Faculty Publications. 246.
Carrano, Andres L. and Brian K. Thorn. The construction of trend-free experimental plans on two-level split-plot designs. Industrial Engineering Research Conference, IERC 2004. May 15-19, 2004. Houston, Texas