Calculating Uncertainty Intervals from Conditional Convex Sets of Probabilities
نویسنده
چکیده
In Moral, Campos (1991) and Cano, Moral, Verdegay-L6pez (1991) a new method of con ditioning convex sets of probabilities has been proposed. The result of it is a convex set of non-necessarily normalized probability dis tributions. The normalizing factor of each probability distribution is interpreted as the possibility assigned to it by the conditioning information. From this, it is deduced that the natural value for the conditional proba bility of an event is a possibility distribution. The aim of this paper is to study methods of transforming this possibility distribution into a probability (or uncertainty) interval. These methods will be based on the use of Sugeno and Choquet integrals. Their behaviour will be compared in basis to some selected exam ples.
منابع مشابه
Conjugate relation between loss functions and uncertainty sets in classification problems
There are two main approaches to binary classification problems: the loss function approach and the uncertainty set approach. The loss function approach is widely used in real-world data analysis. Statistical decision theory has been used to elucidate its properties such as statistical consistency. Conditional probabilities can also be estimated by using the minimum solution of the loss functio...
متن کاملExtreme Lower Probabilities
We consider lower probabilities on finite possibility spaces as models for the uncertainty about the state. These generalizations of classical probabilities can have some interesting properties; for example: k-monotonicity, avoiding sure loss, coherence, permutation invariance. The sets formed by all the lower probabilities satisfying zero or more of these properties are convex. We show how the...
متن کاملExtreme Points of the Credal Sets Generated by Elementary Comparative Probabilities
When using convex probability sets (or, equivalently, lower previsions) as models of uncertainty, identifying extreme points can be useful to perform various computations or to use some algorithms. In general, sets induced by specific models such as possibility distributions, linear vacuous mixture or 2-monotone measures may have extreme points easier to compute than generic convex sets. In thi...
متن کاملCredal Nets with Probabilities Estimated with an Extreme Imprecise Dirichlet Model
The propagation of probabilities in credal networks when probabilities are estimated with a global imprecise Dirichlet model is an important open problem. Only Zaffalon [21] has proposed an algorithm for the Naive classifier. The main difficulty is that, in general, computing upper and lower probability intervals implies the resolution of an optimization of a fraction of two polynomials. In the...
متن کاملA Unifying Framework to Uncertainty Quantification of Polynomial Systems Subject to Aleatory and Epistemic Uncertainty
This article presents a unifying framework to uncertainty quantification for systems subject to several design requirements that depend polynomially on both aleatory and epistemic uncertainties. This methodology, which is based on the Bernstein expansions of polynomials, enables calculating bounding intervals for the range of means, variances and failure probabilities of response metrics corres...
متن کامل