Practical Decipher of Generalized Resolution, Minimum G Aberration and Minimum G2 Aberration  

Oleh:

Yaegaki, Yuhei ; Yasui, Seiichi ; Ojima, Yoshikazu

Jenis: Article from Proceeding
Dalam koleksi: 12th ANQ Congress in Singapore, 5-8 Agustus 2014, page 1-6.
Topik: Experimental Design; Resolution; Minimum Aberration Criterion; Nonregular Design; Defining Relation
Fulltext: QP2-2.1-P0258.pdf (76.47KB)

Isi artikel

Fractional factorial experiments are widely used in various fields as useful technique. Two-level orthogonal arrays are constructed by Hadamard matrices. The orthogonal arrays are classified into regular and nonregular types. Resolution (Box and Hunter, 1961) and Minimum Aberration criterion (Fries and Hunter, 1980) are the evaluation criteria to determine the best design in two-level regular designs. Resolution of the design is calculated by the set of defining relations of the design. Minimum Aberration criterion is used for determining the best design in two-level regular designs with the same value in Resolution. On the other hand, in order to determine the best two-level nonregular design, Generalized Resolution and Minimum G Aberration were proposed by Deng and Tang (1999), and Minimum G2 Aberration was proposed by Tang and Deng (1999). These criteria for two-level nonregular designs are based on J-characteristics of designs. However, those criteria do not give as clear interpretation from the viewpoint of experimental designs as those of regular designs. For example, Resolution III for regular designs means main effects are not confounded with any other main effects but main effects are confounded with two factor interactions. In this paper, we propose defining relations for partial confoundings and describe properties of the evaluation criteria from the viewpoint of experimental design in two-level nonregular designs

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali