Types of uncertainty. Uncertainties from all essential sources must be evaluated and integrated in a basic variable model. Types of uncertainty to be taken into account are: intrinsic physical or mechanical uncertainty statistical uncertainty, when the design decisions are based on a small sample of observations or when there are other similar conditions model uncertainties. The types of probability distributions of the basic variables can be standardised, usually within different classes of decision problems. For example, such standardisations for structural design problems can be found in the Probabilistic Model Code of the Joint Committee on Structural Safety (JCSS 2001).
Types of uncertainty. Many labels are attached to uncertainties but two categories can be used to describe uncertainty: - Aleatory uncertainty, also described as variability or irreducible uncertainty, and - Epistemic uncertainty, also described as uncertainty or reducible uncertainty. Identifying the type of uncertainty provides help in deciding whether and how uncertainties can be reduced. Broadly, uncertainty due to a lack of knowledge can be reduced. Aleatory uncertainty Aleatory uncertainty is stochastic, and a parameterised probability distribution is used to describe this type of uncertainty. The uncertainty is irreducible, as collecting further information would not remove the need to use a distribution over a range of values to describe the quantity. Since aleatory uncertainty cannot be reduced it has to be recognised in an analysis, unless the system can be changed so that the influence of the sources of aleatory uncertainty is reduced. That may not be possible. For example, aleatory uncertainty is intrinsically part of practical atmospheric dispersion. Epistemic uncertainty Epistemic uncertainty involves quantities where there is uncertainty about the value they take which could, in principle, be reduced by the collection of additional information.
