Measurement Decision Risk - The Importance of Definitions

One of the more misunderstood areas of metrology is the Test Uncertainty Ratio (TUR) and its cousin, the Test Accuracy Ratio (TAR). There have been many definitions over the years, but why are these definitions important to a discussion on measurement decision risk? The importance lies in the clarity of communication. Problems can immediately arise in the application (or misapplication) of the definition of these terms. In other words, while it is important to understand the definitions, it is more important to understand concepts behind the definitions and to be precise in how they are applied. The objective of any measurement is a decision. Measurement Decision Risk is a way to look at the quality of a measurement and although it is not a new concept, it has generated a lot of attention since its addition as a requirement in the new U.S. National Standard, ANSI/NCSL Z540.3-2006. In addition to Measurement Decision Risk as the prime method of managing measurement risk, Z540.3 has also added, as a fall-back, an explicit definition for TUR. The impact these changes might have on calibration service providers if these requirements are levied on them has become the topic of much discussion and in some cases concern. This paper looks at the concepts behind the definitions and how they relate to Measurement Decision Risk. Using common examples, this paper will also provide a comparison of various elements of risk related to measurement science using the concepts of TAR, TUR, accuracy ratios, and Consumer Risk (False Accept Risk). The goal is to provide a better understanding of their relevance to the measurement decision process.