Towards a Normative Theory of Scientific Evidence

TL;DR

This paper introduces a reasoning system that derives probability intervals from objective evidence like experiments and axioms, aiming to improve decision-making in scientific and diagnostic domains.

Contribution

It generalizes Nilsson's probabilistic logic to handle probability intervals and experimental data, enabling better management of uncertainty in scientific reasoning.

Findings

Derives probability intervals from diverse evidence sources

Manages uncertainty in data and rules within a rule-based system

Applicable to medical diagnosis and scientific analysis

Abstract

A scientific reasoning system makes decisions using objective evidence in the form of independent experimental trials, propositional axioms, and constraints on the probabilities of events. As a first step towards this goal, we propose a system that derives probability intervals from objective evidence in those forms. Our reasoning system can manage uncertainty about data and rules in a rule based expert system. We expect that our system will be particularly applicable to diagnosis and analysis in domains with a wealth of experimental evidence such as medicine. We discuss limitations of this solution and propose future directions for this research. This work can be considered a generalization of Nilsson's "probabilistic logic" [Nil86] to intervals and experimental observations.