The Development of a Method for Constructing Super Saturated Design and Nearly Orthogonal Design with Mixed Level Orthogonal Design

Abstract

Orthogonal arrays such as factorial and fractional factorial designs of experimental plans are used for identifying important factors to improve quality of an experiment. Super Saturated Designs are very cost-effective in the stage of scientific investigations. Nearly-Orthogonal Arrays that can construct a variety of small-run designs with different levels have good statistical properties. In the present paper Super Saturated Design and Nearly Orthogonal Design are constructed with Orthogonal Design. It is a great deal of interest in the development of factor screening experiments that are optimal or highly efficient under the E (s²) and J₂ criterion. We focus on finding combinatorial solution of the experiment. We proposed a class of special super saturated design using Hadamard design on thalassemic children’s data and constructed mixed level orthogonal arrays and nearly orthogonal arrays.