Premium
A Comparative Analysis of the Performance of Taguchi's Linear Graphs for the Design of Two‐Level Fractional Factorials
Author(s) -
Bisgaard Søren
Publication year - 1996
Publication title -
journal of the royal statistical society: series c (applied statistics)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.205
H-Index - 72
eISSN - 1467-9876
pISSN - 0035-9254
DOI - 10.2307/2986090
Subject(s) - taguchi methods , mathematics , statistics , fractional factorial design , combinatorics , factorial experiment
SUMMARY In this paper conventional concepts of aliases and confounding are used to analyse several two‐level fractional factorial designs constructed with the use of Taguchi's linear graph technique. Taguchi's designs are subsequently compared with more conventional alternatives and it is shown that the latter often are better in terms of resolution and are more robust to assumptions that are likely to be violated in practice. We also comment on the practice of making prior assumptions based on engineering knowledge about which two‐factor interactions are active. We conclude that, although the linear graph method has other applications, the need for this method for the design of two‐level fractional factorials is limited, that the designs obtained are non‐robust and that better and simpler conventional alternatives exist.