Premium
Bootstrap Analysis of Designed Experiments
Author(s) -
Kenett Ron S.,
Rahav Effi,
Steinberg David M.
Publication year - 2006
Publication title -
quality and reliability engineering international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.913
H-Index - 62
eISSN - 1099-1638
pISSN - 0748-8017
DOI - 10.1002/qre.802
Subject(s) - bootstrapping (finance) , heteroscedasticity , computer science , econometrics , statistics , data mining , operations research , machine learning , engineering , mathematics
In the first ENBIS conference in Oslo, Kenett and Steinberg (On the application of bootstrapping in analyzing designed experiments. Proceedings of the 1st Annual Conference on Business and Industrial Statistics, Oslo, Norway, 17–18 September 2001) proposed the application of bootstrapping to the analysis of data derived from moderate size designed experiments. In this paper we present follow‐up work with an emphasis on designed experiments with censored data, heteroscedasticity and constraints related to the structure of the experiment. Our results show clear advantages to bootstrap‐based data analysis, which is both robust and relatively easy to apply. The bootstrap analysis often points to problems in linear model analyses that might easily be overlooked. These findings suggest that bootstrapping can contribute significantly to the design of experiments methodology. Copyright © 2006 John Wiley & Sons, Ltd.