Title: On the selection of significant variables from unreplicated factorial designs

Authors: Nuno Ricardo Costa; José Palma; Zulema Lopes Pereira

Addresses: Instituto Politécnico de Setúbal, Escola Superior de Tecnologia de Setúbal, Estefanilha, Campus do IPS, 2910-761 Setúbal – Portugal; UNIDEMI/DEMI, Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa, Monte de Caparica, 2829-516 Caparica – Portugal ' Instituto Politécnico de Setúbal, Escola Superior de Tecnologia de Setúbal, Estefanilha, Campus do IPS, 2910-761 Setúbal – Portugal ' UNIDEMI/DEMI, Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa, Monte de Caparica, 2829-516 Caparica – Portugal

Abstract: Separation of the few control factors with significant effect from the remaining ones at the early phase of experimental studies is a recommended practice for systems development and improvement. The normal probability plot is a widely accepted graphical technique for screening, although it does not provide a unique interpretation of results in some cases. Thus, more formal procedures have been proposed to supplement it. The performance of popular methods along with lesser known and used ones is assessed using four evaluation standards based on a simulation study. The results show that Al-Shiha and Yang's method stands out as the best performer when compared with other computational methods so it is the best choice to supplement the often used graphical technique. A strategy for analysing unreplicated fractional factorial designs is also outlined.

Keywords: individual error rate; IER; probability plot; numerical methods; screening; simulation; unreplicated fractional factorial design; evaluation standards; factorial design; experimental design.

DOI: 10.1504/IJPQM.2013.055551

International Journal of Productivity and Quality Management, 2013 Vol.12 No.2, pp.161 - 184

Published online: 31 Mar 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article