A0550
Title: Balanced orthogonal equivalent estimation split-plot designs
Authors: Po Yang - University of Manitoba (Canada) [presenting]
Abstract: Many industrial experiments involve factors whose levels are hard or costly to change. In such cases, split-plot designs are often employed. To estimate model parameters, generalized least squares is typically used. However, for certain split-plot designs, the generalized least squares estimator is equivalent to the ordinary least squares estimator. As a result, estimating variance components is unnecessary when estimating model parameters. These designs are referred to as equivalent estimation designs. Using integer programming methods, a catalog of three-level balanced orthogonal split-plot designs is constructed, in which main effects and second-order effects are not aliased. The performance of the selected designs is then evaluated using various criteria.
