Construction of Minimal-Point Mixed-Level Screening Designs Using Conference Matrices

Abstract

Screening designs are frequently used to identify active effects from a large number of factors. Small size designs are preferred when the experiments are costly. Two-level or three-level minimal-point screening designs have been well studied in the literature. However, minimal-point mixed-level designs have not been thoroughly explored. In this paper, a new class of minimal-point mixed-level designs is constructed using conference matrices. The constructed designs can be used to estimate the main effects and quadratic effects with a good performance of D-efficiency and variance of estimates.

• D-Efficiency
• Main Effect
• Maximal Determinant Matrix
• Orthogonal Array
• Quadratic Effect

Additional information

Notes on contributors

Jinyu Yang

Dr. Yang is Assistant Professor in the Institute of Statistics at Nankai University. Her email address is [email protected].

Dennis K. J. Lin

Dr. Lin is University Distinguished Professor of Statistics at Penn State University. He is a Fellow of ASQ and ASA. His email address is [email protected].

Min-Qian Liu

Dr. Liu is Professor in the Institute of Statistics at Nankai University. His email address is [email protected].