Generalized Conditioning in Neighbourhood Models

Sets of probability measures which form neighbourhoods of classical probability measures are studied. An application of Jeffrey’s rule of conditioning to forming neighbourhoods of probability measures is proposed. Neighbourhoods that are closed for generalized conditioning according to this rule are characterized. They are shown to be exactly convex and bi-elastic neighbourhoods. Keywords. interval probability, robust statistics, non-additive probabilities, neighbourhood models

• Type: Conference
• Year: 2005
• Where: ISIPTA
• Authors: Damjan Skulj
• Keywords: Bi-elastic Neighbourhoods, Classical Probability Measures, ISIPTA 2005, Mathematics, Probability Measures