A CLASS OF MULTILEVEL NONREGULAR DESIGNS FOR STUDYING QUANTITATIVE FACTORS

Fractional factorial designs are widely used for designing screening experiments. Nonregular fractional can have better properties than regular designs, but their construction is challenging. Current research on the of nonregular focuses two-level designs. We provide a novel class multilevel by permuting levels develop theory illustrating how be permuted without computer search and accordingly propose sequential method constructing Compared to these more accurate estimations effects efficient experiments with quantitative factors. further explore space-filling property obtained demonstrate superiority.