Making Decisions Using Sets of Probabilities: Updating, Time Consistency, and Calibration

by   Peter D. Grünwald, et al.

We consider how an agent should update her beliefs when her beliefs are represented by a set P of probability distributions, given that the agent makes decisions using the minimax criterion, perhaps the best-studied and most commonly-used criterion in the literature. We adopt a game-theoretic framework, where the agent plays against a bookie, who chooses some distribution from P. We consider two reasonable games that differ in what the bookie knows when he makes his choice. Anomalies that have been observed before, like time inconsistency, can be understood as arising because different games are being played, against bookies with different information. We characterize the important special cases in which the optimal decision rules according to the minimax criterion amount to either conditioning or simply ignoring the information. Finally, we consider the relationship between updating and calibration when uncertainty is described by sets of probabilities. Our results emphasize the key role of the rectangularity condition of Epstein and Schneider.



There are no comments yet.


page 1

page 2

page 3

page 4


A Game-Theoretic Analysis of Updating Sets of Probabilities

We consider how an agent should update her uncertainty when it is repres...

Updating Sets of Probabilities

There are several well-known justifications for conditioning as the appr...

Dynamic Precise and Imprecise Probability Kinematics

We introduce a new method for updating subjective beliefs based on Jeffr...

Using Clinical Experts Beliefs to Compare Survival Models in Health Technology Assessment

Objectives: The aim of this paper is to contrast the retrospective and p...

Unforeseen Evidence

I proposes a normative updating rule, extended Bayesianism, for the inco...

Probability Estimation in Face of Irrelevant Information

In this paper, we consider one aspect of the problem of applying decisio...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.