• • 上一篇    

一般最小低阶混杂设计的试验安排

周琦, 罗佳玲, 黄楚津, 刘盼盼   

  1. 天津财经大学统计学院, 天津 300222
  • 收稿日期:2022-03-03 修回日期:2022-04-19 发布日期:2022-08-31
  • 通讯作者: 罗佳玲,Email:lllljl20212021@163.com.
  • 基金资助:
    国家自然科学基金(11971345,11501405,11601366,11701088),天津市"131"人才工程、天津市中青年骨干创新人才培养计划资助项目和天津市研究生科研创新项目(2021YJSS303)资助课题.

周琦, 罗佳玲, 黄楚津, 刘盼盼. 一般最小低阶混杂设计的试验安排[J]. 系统科学与数学, 2022, 42(7): 1866-1876.

ZHOU Qi, LUO Jialing, HUANG Chujin, LIU Panpan. The Experimental Planning of General Minimum Lower-Order Confounding Designs[J]. Journal of Systems Science and Mathematical Sciences, 2022, 42(7): 1866-1876.

The Experimental Planning of General Minimum Lower-Order Confounding Designs

ZHOU Qi, LUO Jialing, HUANG Chujin, LIU Panpan   

  1. School of Statistics, Tianjin University of Finance and Economics, Tianjin 300222
  • Received:2022-03-03 Revised:2022-04-19 Published:2022-08-31
为了更好地应用二水平因子试验估计试验者所关注的因子效应,一般最小低阶混杂(GMC)准则被提出并用于选取最优设计,称为GMC设计.文章旨在研究满足$N/4+2\le n\le 5N/16$GMC设计的试验安排问题,首先给出了满足$N/4+2\le n\le 5N/16$的GMC$2^{n-m}$设计中各列根据{因子别名效应数型}排序的理论结果,然后讨论了在少数因子较为重要这一先验信息下,将这些重要因子安排到GMC设计列上的方法.
To effectively estimate important effects in two-level factorial experiments, the general minimum lower order confounding (GMC) criterion was proposed to select factorial designs, called GMC designs. This paper aims at studying the experimental planning of GMC $2^{n-m}$ designs with $N/4+2\le n \le 5N/16$. At first, we propose the theoretical results of the column ranking of GMC $2^{n-m}$ designs with $N/4+2\le n \le 5N/16$ based on their factor aliased effect-number pattern. Then, under the prior information that some factors are more important, we provide the guidance on the assignment of these factors to specific columns of GMC designs. Finally, we make the conclusion of this paper and discuss some future work.

MR(2010)主题分类: 

()
[1] Box G E P, Hunter J S.The 2k-p fractional factorial designs I and II.Technometrics, 1961, 3:311-351, 449-458.
[2] Fries A, Hunter W G.Minimum aberration 2k-p designs.Technometrics, 1980, 22:601-608.
[3] Zhang R C, Li P, Zhao S L, et al.A general minimum lower-order confounding criterion for two-level regular designs.Statist Sinica, 2008, 16:1689-1705.
[4] Wu C F J, Hamada M.Experiments:Planning, Analysis and Parameter Design Optimization.New York:Wiley, 2010.
[5] Zhou Q, Balakrishnan N, Zhang R C.Factor aliased effect number pattern and experimental planning.Canadian Journal of Statistics, 2013, 41:540-555.
[6] Li W, Zhou Q, Zhang R C.Effective designs based on individual word length patterns.Journal of Statistical Planning and Inference, 2015, 163:43-47.
[7] Li W, Mee R, Zhou Q.Using individual factor information in fractional factorial designs.Technometrics, 2019, 61:38-49.
[8] Li P F, Zhao S L, Zhang R C.A theory on constructing 2n-m designs with general minimum lower-order confounding.Statist Sinica, 2011, 21:1571-1589.
[9] Zhang R C, Cheng Y.General minimum lower order confounding designs:An overview and a construction theory.J.Statist.Plann.Inference, 2010, 140:1719-1730.
[10] Cheng Y, Zhang R C.On construction of general minimum lower-order confounding 2n-m designs with N/4+1 ≤ n ≤ 9N/32.J.Statist.Plann.Inference, 2010, 140:2384-2394.
[11] Chen J, Liu M Q.Some theory for constructing general minimum lower order confounding designs.Statist Sinica, 2011, 21:1541-1555.
[12] 周琦,杨雪.一类纯净折衷设计的构造及其性质.中国科学:数学, 2022, 52(5):583-592.(Zhou Q, Yang X.The construction and properties of a class of clear compromise designs.Sci.Sin.Math., 2022, 52(5):583-592.)
[13] 周琦,刘盼盼.一般最小低阶混杂设计的统计性质.应用数学学报, 2022, 45(1):19-30.(Zhou Q, Liu P P.The statistical properties of general minimum lower-order confounding designs.Acta Mathematicae Applicatae Sinica, 2022, 45(1):19-30.)
[1] 周琦, 张蕊. 最小低阶混杂准则下纯净折衷设计的构造[J]. 系统科学与数学, 2021, 41(9): 2612-2620.
阅读次数
全文


摘要