Finding the Important Factors Among Many Factors in Designed Experiments

Often in industrial experimentation there are a large number of factors to be considered, even though only a few are important (effect sparcity). Several techniques have been proposed for screening the important factors, but each has its limitations. We propose a new adaptive screening technique using a genetic algorithm by construction of an optimal supersaturated design from the Hadamard matrix. In this paper, we concentrate on construction of an optimal SSD.