Transferable belief model
The transferable belief model (TBM) is a model developed to represent quantified beliefs, or equivalently justified beliefs or supports. It is based on the use of belief functions. It concerns the same domain that is treated in probability theory by the use of probability functions. The probability model is not restricted to the modelization of the psychological process of believing and neither is the TBM. It is applicable to most of the problems where uncertainty is present. It is not intended to replace probability models when the source of uncertainty can be found in some underlying physical random process in which case probability models are of course adequate. The TBM is relevant to those situations where non random uncertainty is present, the prototypical example being the case where data are collected from partially reliable sources.