Exploratory Data Analysis in Quality-Improvement Projects

Abstract

The aim of this paper is to provide a prescriptive framework for exploratory data analysis (EDA) in quality-improvement projects. The framework is developed on the basis of a large number of real-life applications. The three steps of EDA are described: display the data, identify salient features, and interpret salient features. Graphical display of data, Shewhart's assignable causes, the maximum entropy principle, abduction, and explanatory coherence all are part of the resulting framework. Furthermore, the roles of probabilistic reasoning and automatic statistical procedures in EDA are discussed.