Complex problems with incomplete evidence: Modelling for decision-making

A wide variety of models are generally used to help in decision making. With reference to the parameters and structure of a model, four basic types can be identified depending on the degrees of vagueness and completeness. We propose that epistemic probability, firmly rooted in the concept of probability as an attribute of opinion and argument, is an appropriate way to handle problems where there are significant issues of incompleteness and vagueness in the modeling. Uncertainty is handled in an effective manner through argument and justification.