An evaluation of probabilistic approaches to inference to the best explanation

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper presents results of computer simulations for a number of different probabilistic versions of inference to the best explanation (IBE), which are distinguished by the probabilistic measures used to identify the best explanation. Simulation results are presented which include cases involving ignorance of a catch-all hypothesis, uncertainty regarding the prior probability distribution over the remaining hypotheses, initial elimination of implausible hypotheses, and variations in the number of pieces of evidence taken into consideration. The results show that at least some versions of IBE perform very well in a wide range of cases. In particular, the results for all approaches remain very similar (or improve in some cases) when just the two hypotheses with the highest prior probabilities are retained and the rest are eliminated from consideration.
LanguageEnglish
Pages184-194
Number of pages11
JournalInternational Journal of Approximate Reasoning
Volume103
Early online date17 Sep 2018
DOIs
Publication statusPublished - Dec 2018

Fingerprint

Probabilistic Approach
Probability distributions
Prior Probability
Computer simulation
Evaluation
Prior distribution
Elimination
Probability Distribution
Computer Simulation
Uncertainty
Range of data
Simulation

Keywords

  • Explanation
  • Abduction
  • Bayesian inference
  • Computer simulation

Cite this

@article{bfa0ed3687ca420f86f7c2ff9004fdbe,
title = "An evaluation of probabilistic approaches to inference to the best explanation",
abstract = "This paper presents results of computer simulations for a number of different probabilistic versions of inference to the best explanation (IBE), which are distinguished by the probabilistic measures used to identify the best explanation. Simulation results are presented which include cases involving ignorance of a catch-all hypothesis, uncertainty regarding the prior probability distribution over the remaining hypotheses, initial elimination of implausible hypotheses, and variations in the number of pieces of evidence taken into consideration. The results show that at least some versions of IBE perform very well in a wide range of cases. In particular, the results for all approaches remain very similar (or improve in some cases) when just the two hypotheses with the highest prior probabilities are retained and the rest are eliminated from consideration.",
keywords = "Explanation, Abduction, Bayesian inference, Computer simulation",
author = "Glass, {David H.}",
year = "2018",
month = "12",
doi = "10.1016/j.ijar.2018.09.004",
language = "English",
volume = "103",
pages = "184--194",

}

An evaluation of probabilistic approaches to inference to the best explanation. / Glass, David H.

Vol. 103, 12.2018, p. 184-194.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An evaluation of probabilistic approaches to inference to the best explanation

AU - Glass, David H.

PY - 2018/12

Y1 - 2018/12

N2 - This paper presents results of computer simulations for a number of different probabilistic versions of inference to the best explanation (IBE), which are distinguished by the probabilistic measures used to identify the best explanation. Simulation results are presented which include cases involving ignorance of a catch-all hypothesis, uncertainty regarding the prior probability distribution over the remaining hypotheses, initial elimination of implausible hypotheses, and variations in the number of pieces of evidence taken into consideration. The results show that at least some versions of IBE perform very well in a wide range of cases. In particular, the results for all approaches remain very similar (or improve in some cases) when just the two hypotheses with the highest prior probabilities are retained and the rest are eliminated from consideration.

AB - This paper presents results of computer simulations for a number of different probabilistic versions of inference to the best explanation (IBE), which are distinguished by the probabilistic measures used to identify the best explanation. Simulation results are presented which include cases involving ignorance of a catch-all hypothesis, uncertainty regarding the prior probability distribution over the remaining hypotheses, initial elimination of implausible hypotheses, and variations in the number of pieces of evidence taken into consideration. The results show that at least some versions of IBE perform very well in a wide range of cases. In particular, the results for all approaches remain very similar (or improve in some cases) when just the two hypotheses with the highest prior probabilities are retained and the rest are eliminated from consideration.

KW - Explanation

KW - Abduction

KW - Bayesian inference

KW - Computer simulation

U2 - 10.1016/j.ijar.2018.09.004

DO - 10.1016/j.ijar.2018.09.004

M3 - Article

VL - 103

SP - 184

EP - 194

ER -