Maximum Uncertainty Procedures for Interval-Valued Probability Distributions

TL;DR

This paper introduces measures of uncertainty for interval-valued probability distributions, proposes a maximum uncertainty inference method for marginals, and develops a technique for reconstructing distributions from projections.

Contribution

It presents a novel maximum uncertainty inference procedure and a reconstruction technique for interval distributions, advancing the analysis of uncertain probabilistic data.

Findings

Mathematical properties of uncertainty measures are established.

A maximum uncertainty inference procedure for marginals is developed.

A reconstruction technique from projections is introduced.

Abstract

Measures of uncertainty and divergence are introduced for interval-valued probability distributions and are shown to have desirable mathematical properties. A maximum uncertainty inference procedure for marginal interval distributions is presented. A technique for reconstruction of interval distributions from projections is developed based on this inference procedure