Analysis Considerations in Industrial Split-Plot Experiments with Non-Normal Responses

Journal of Quality Technology vol. 36 issue 2 - April 2004

Abstract: [This abstract is based on the authors' abstract.] When factors exist whose levels are difficult or costly to control, industrial experiments are typically run within a split-plot context. Generalized linear models have been suggested for the analysis of completely randomized designs when the response is non-normal, but a completely randomized design implies that the responses are independent. In split-plot experiments it is assumed that responses within the whole plot are correlated. Generalized linear mixed models (GLMM) are able to account for this correlation during analysis. Two categories of GLMM are investigated and contrasted, using an example from film manufacturing.

Keywords: Linear models - Mixture experiments - Non-normality - Response model - Split-plot design

Access this article
Other ways to access this article
You will need Adobe Reader to view this PDF document. Download the free Reader from Adobe

Featured advertisers


(0) Member Reviews

Featured advertisers

ASQ is a global community of people passionate about quality, who use the tools, their ideas and expertise to make our world work better. ASQ: The Global Voice of Quality.