Must a Process Be in Statistical Control before Conducting Designed Experiments

Quality Engineering vol. 20 issue 2 - April 2008

Abstract: [This abstract is based on the author’s abstract.] Seventy-five years ago it was demonstrated that the key concepts of randomization, blocking, and replication make it possible to conduct experiments on processes that may not be in a state of statistical control. Yet even today confusion remains about the need for statistical control as a prerequisite for conducting valid industrial experiments. This article reviews and extends the original argument, reusing the original examples to discount the need for statistical control as a prerequisite in industrial experiments. Clarifying this issue may encourage quality practitioners to find wider use for designed experiments.

Keywords: Analysis of variance (ANOVA) - Blocking - Design of experiments (DOE) - Randomization tests - Replication

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

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.