## Research Abstracts Online

January
2008 - March 2009

### University of Minnesota Twin Cities

Curtis. L. Carlson School of Management

Department of Operations and Management Science

## PI: William Li, Associate Fellow

Co-PI: Christopher J. Nachtsheim

### Bayesian Model-robust Designs and Optimal Split-point Designs

These researchers have been involved in three projects during this period. The first discusses a Bayesian approach to model-robust designs, which are efficient over a class of possible models. Extending their previous work, the researchers are introducing an idea that uses the traditional Bayesian design method for parameter estimation and incorporates a discrete prior probability on the set of models of interest.

A new project begun this period considered supersaturated designs, which are used when there are more factors than runs, and which are especially useful at early stage of a project. In the area of supersaturated designs, most attention has been given on the construction of the efficient supersaturated designs in the literature. On the analysis of supersaturated designs, while many traditional model selection methods are applicable, the literature has been pessimistic and has suggested that these methods should only be used with caution. These researchers are comparing several model selection methods, including all-subset, stepwise, LASSO, and sparse sliced inverse regression.

The final project, completed during this period, involved split-plot experiments, which may be used when it is impractical to completely randomize the treatment combinations of a designed experiment. Existing literature almost exclusively focused upon the construction and selection of optimal two-level regular split-plot designs. To provide more flexible design choices in the split-plot setting, the researchers explored the use of nonregular two-level split-plot designs having 12, 16, 20, and 24 runs and between one to three whole-plot factors.

### Group Member

Kenny Ye, Department of Epidemiology and Population Health, Albert Einstein College of Medicine, Bronx, New York, New York