An epistemological view of decision-aid technology with emphasis on expert systems

The philosophical foundations of statistics, operations research, and expert systems are explored, using the notion of metaphor. The authors develop the idea that a root metaphor or a world view exists in both the decision maker and the decision-aid technologies available to solve a problem. To solve a problem correctly, a decision maker must not only use a decision aid correctly, but also first choose the correct decision aid. When an inappropriate decision aid is used, it creates the possibility of so-called type III errors: reaching a wrong solution even though the procedures were followed correctly. As decision aids become both more sophisticated and more user-friendly, they become available for use by more and more naive users, and the possibility of type III errors increases. In addition, as expert systems become more prominent, it is important to be aware of the philosophical biases of the expert and the knowledge engineer as they interact to develop an expert system. A framework is developed that decision makers can use to help them compare the characteristics of various decision aids and choose the most appropriate for solving a particular problem