Author Description

Accurate measurements in clinical and industrial testing are often not possible. Each measurement contains what can be regarded as containing an uncontrollable component of error. Their use to control quality therefore inevitable leads to right and wring conclusions. This book describes methods which can be used to control the frequency with which these occur. It describes recent developments which can be employed when very few control measurements can be taken due to limitations of cost or technical difficulty. It begins by describing simple statistical decision rules which were initially used to control the quality of industrial processes. These then form a basis on which to describe the concepts and practical consequences of the use of statistical quality control. It then illustrates improvements in the property of decision rules which can be achieved with appropriate choices of control rule parameters, test statistics and methods of control which selectively utilize information contained in the test data which is indicating that a change in quality level had occurred.