User-friendly statistical concepts for process monitoring

Many standard statistical process control techniques involve sophisticated mathematical concepts, which are frequently misunderstood and misused by their users. This means, as this paper argues, that the techniques, and the terminology and concepts underlying them, are inappropriate for their intended uses and users. The paper considers the areas of the statistical background which cause difficulties. It goes on to describe some alternative concepts, techniques and terminology, which are likely to be conceptually simpler and more ‘user-friendly’ (and in some cases more accurate and robust). None of the ideas require users to be familiar with the standard deviation. We also suggest that the approach of reengineering the conceptual background to suit the context of users and uses may be appropriate to other areas of practical statistics and OR. The paper identifies some general principles for achieving this.