Approaches to the Data Coherence Diagnosis in Bayesian Belief Network Models

Bayesian belief networks provide the ability to combine different types of information, e.g. statistical or expert data, allow working with incomplete or inaccurate information; they have clarity and other useful properties. Due to this, Bayesian belief networks have become a popular and highly effective tool in many fields of research. However, in many research areas data provided by the experts can be incoherent, and so in some tasks one should use tools to verify their coherence. The paper discusses examples of application of the Bayesian belief networks in medicine and public health, ecology, economics and risk analysis, functional safety, sociology, and other research areas, and shows the need to develop methods to check the coherence of initial data. The purpose of this work is to systematize problems and examples that illustrate the use of Bayesian belief networks by reviewing and to assess their use of data coherence diagnosis and its importance.