There are enormous numbers of models which are based on deterministic variables such as constant parameters, physic coefficients, material properties, biological data, etc. In these models, there are parameters which are considered constants but they are not.

Bayesian approaches to these parameters improve the quality of the results. Many of the pass/fail outcomes are simplifications of more valuable information which is sometimes wrongly dismissed. These simplifications in addition to other factors can lead to a misleading conclusion.

When the engineering problem is calculated with safety factors no critical fails may occur, this is one of the reasons why they are so important. However, in certain cases, the information should not be dismissed. Sometimes it is a matter of a number of degrees of freedoms or computing performance that compel researchers to make simplifications.

Many recent analyses apply new techniques (such as Monte Carlo) to connect deterministic to random approaches (Bayesian distributions). The objective of this special issue is to develop new methods in almost any field in order not to dismiss valuable information due to inappropriate simplifications.