Imprecise second-order model for a system of independent random variables

  • Authors:
  • Lev V. Utkin

  • Affiliations:
  • Department of Computer Science, Forest Technical Academy, St. Petersburg, Russia

  • Venue:
  • International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

A new hierarchical uncertainty model for combining different evidence about a system of statistically independent random variables is studied in the paper. It is assumed that the first-order level of the model is represented by sets of lower and upper previsions (expectations) of random variables and the second-order level is represented by sets of lower and upper probabilities which can be viewed as confidence weights for interval-valued expectations of the first-order level. The model is rather general and allows us to compute probability bounds and "average" bounds for previsions of a function of random variables. A numerical example illustrates this model.