Updating with incomplete observations

08/07/2014
by   Gert de Cooman, et al.
0

Currently, there is renewed interest in the problem, raised by Shafer in 1985, of updating probabilities when observations are incomplete (or set-valued). This is a fundamental problem, and of particular interest for Bayesian networks. Recently, Grunwald and Halpern have shown that commonly used updating strategies fail here, except under very special assumptions. We propose a new rule for updating probabilities with incomplete observations. Our approach is deliberately conservative: we make no or weak assumptions about the so-called incompleteness mechanism that produces incomplete observations. We model our ignorance about this mechanism by a vacuous lower prevision, a tool from the theory of imprecise probabilities, and we derive a new updating rule using coherence arguments. In general, our rule produces lower posterior probabilities, as well as partially determinate decisions. This is a logical consequence of the ignorance about the incompleteness mechanism. We show how the new rule can properly address the apparent paradox in the 'Monty Hall' puzzle. In addition, we apply it to the classification of new evidence in Bayesian networks constructed using expert knowledge. We provide an exact algorithm for this task with linear-time complexity, also for multiply connected nets.

READ FULL TEXT

page 1

page 2

page 4

page 5

page 6

research
06/15/2019

From Incomplete, Dynamic Data to Bayesian Networks

Bayesian networks are a versatile and powerful tool to model complex phe...
research
12/24/2017

Judicious Judgment Meets Unsettling Updating: Dilation, Sure Loss, and Simpson's Paradox

Statistical learning using imprecise probabilities is gaining more atten...
research
03/27/2013

Independence and Bayesian Updating Methods

Duda, Hart, and Nilsson have set forth a method for rule-based inference...
research
01/15/2014

Conservative Inference Rule for Uncertain Reasoning under Incompleteness

In this paper we formulate the problem of inference under incomplete inf...
research
03/28/2013

Advantages and a Limitation of Using LEG Nets in a Real-TIme Problem

After experimenting with a number of non-probabilistic methods for deali...
research
10/07/2015

Towards a general framework for an observation and knowledge based model of occupant behaviour in office buildings

This paper proposes a new general approach based on Bayesian networks to...
research
04/26/2023

Regression with Sensor Data Containing Incomplete Observations

This paper addresses a regression problem in which output label values a...

Please sign up or login with your details

Forgot password? Click here to reset