Identification of Significant Treatment Effects in Unreplicated Factorial Experiments.
No Thumbnail Available
Date
2006
Journal Title
Journal ISSN
Volume Title
Publisher
Published by Biometrics Association of Nigeria.
Abstract
Unreplicated factorial designs are used in industrial and other real-life experiments due to costs consideration or some other reasons. Normal plot has been an important technique of identifying significant treatment effects. However, two other methods of identifying significant effects namely, Lenth and Step-Down Lenth methods are examined in this paper. The three methods are compared in terms of their performance in identifying significant effects by simulating unreplicated 24 factorial designs at two different settings. In evaluating the three methods, we observed that Normal plot has the overall best performance, but the three methods are similar when the magnitude of each of the effects is high.
Description
Keywords
Pseudo-Standard Error, Significant Effect, Treatment Contrast, Un-replicated Factorial Experiment
Citation
Journal of the Biometrics Association of Nigeria, BIOMATA