Optimal measurement policy for decision making: a case study of quality management based on laboratory measurements

Measurement information generates value, when it is applied in the decision making. An investment cost and maintenance costs are associated with each component of the measurement system. Clearly, there is - under a given set of scenarios - a measurement setup that is optimal in expected (discounted) utility. Contrary to process design, design of measurement and information systems has not been formulated as such an optimization problem, but has rather been tackled intuitively. In this presentation we propose a framework for analyzing such an optimization problem. Our framework is based on that the basic mechanism of measurement is reduction of uncertainty about reality. Statistical decision theory serves as the basis for analyzing decision making. In this article we apply the framework to a problem that is rather simple but of practical importance: how to arrange laboratory quality measurements optimally. In particular, we discuss a case in the paper making industry, in which the product quality is measured with automated quality analyzers and by laboratory measurements.