摘要
均匀试验设计是部分因子设计的主要方法之一,已被广泛地应用于工业生产、系统工程、制药及其他自然科学中。各种偏差被用来度量部分因子设计的均匀性。不管使用哪种偏差,关键的问题是寻找一个精确的偏差下界,因为它可以作为衡量设计均匀性的标准。本文给出了对称因子设计中心化L2-偏差在3-水平下的另一个下界,是对参考文献[15]结论的一个补充。
Uniform experiment design is one of main methods tbr ti^actional tactonal oeslgns, wmcn has been widely applied in manufacturing, system engineering, pharmaceutics and natural sciences. Many kinds of discrepancies have been used in valuing uniformity of fractional factorial designs. No matter us- ing which discrepancy, the key is to provide an accurate discrepancy lower bound, because it may be as a criterion to value uniformity of designs. In this paper, a new lower bound of centered -discrepancy on three-level symmetric factorial designs is provided, it makes up the result in [15].
关键词
3-水平
部分因子设计
中心化L2-偏差
下界
three-level
fractional factorial designs
centered -discrepancy
lower bound.