Title: Robust split-plot designs for model misspecification
Authors: Chang-Yun Lin - National Chung Hsing University (Taiwan) [presenting]
Abstract: Many existing methods for constructing optimal split-plot designs, such as D-optimal or A-optimal designs, only focus on minimizing the variance of the parameter estimates for the fitted model. However, the true model is usually more complicated and, hence, the fitted model is often misspecified. If there exist significant effects that are not included in the model, then the estimates could be highly biased. Therefore, a good split-plot design should be able to simultaneously control the variance and the bias of the estimates. We propose a new method for constructing optimal split-plot designs that are robust under model misspecification. Four examples are provided to demonstrate that our method can produce efficient split-plot designs with smaller overall aliasing. Simulation studies are performed to verify that the robust designs we construct have high power, low false discovery rate, and small mean squared error.