Design for Computer Experiments with Qualitative and Quantitative Factors

• Activity Number: 627
• Type: Topic Contributed
• Date/Time: Thursday, August 8, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Quality and Productivity Section
• Author(s): Chunfang Lin*+ and Xinwei Deng and Ying Hung
• Companies: Queen's University and Virginia Tech and Department of Statistics, Rutgers University
• Keywords: Computer Experiment ; Orthogonal Array ; Space-Filling Design

Abstract

Latin hypercubes are popular choices for computer experiments. Sliced Latin hypercubes were proposed to design computer experiments with qualitative and quantitative variables. Such a design is a special Latin hypercube design that can be partitioned into slices of smaller Latin hypercube designs. Sliced Latin hypercube designs are often suitable for experiments with a small number of qualitative variables. To design experiments with a flexible number of qualitative variables, we introduce a new class of Latin hypercubes, called marginal sliced Latin hypercubes. Several constructions will be discussed.