PRACTICAL APPROACH TO CALCULATING PROBABILITY OF FALSE ACCEPT FOR DECISION RULES IN CONFORMITY ASSESSMENT

The decision rule, as defined in the ISO/IEC 17025 standard, is a rule that describes how measurement uncertainty is taken into account when stating conformity with a specified requirement (1). Essentially, it is a rule which is based on the idea of how much risk should be accepted when starting to use an item. In other words, the decision rule is fundamentally concerned with the question of what is the acceptable level of risk. The concept of risk here represents the probability of accepting an item that actually doesnt conform with specification (false accept) or the probability of rejecting an item that actually conforms with specification (false reject). Risk, by its nature, can never be reduced to zero,it can only be close to zero. Due to its consequences, false accept of an item is a more undesirable situation than false reject. Therefore, when a facility decides that an item is suitable for use, the acceptable level of probability of false accept which is also known as specific risk should be determined (2). This acceptable level is the facility s choice and may vary depending on the business objective.The aim of this article is to analyze a conformity assessment of an item based on sample calibration results by using binary statement (passfail) decision rule, to calculate acceptable specific risk levels when starting to use an item and to serve as a supplementary document to conformity assessment documents.