How to model mutually exclusive events based on independent causal pathways in Bayesian network models. Fenton, N., Neil, M., Lagnado, D., Marsh, W., Yet, B., & Constantinou, A. Knowledge-Based Systems, 113:39 - 50, 2016. ![How to model mutually exclusive events based on independent causal pathways in Bayesian network models [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Abstract We show that existing Bayesian network (BN) modelling techniques cannot capture the correct intuitive reasoning in the important case when a set of mutually exclusive events need to be modelled as separate nodes instead of states of a single node. A previously proposed `solution', which introduces a simple constraint node that enforces mutual exclusivity, fails to preserve the prior probabilities of the events, while other proposed solutions involve major changes to the original model. We provide a novel and simple solution to this problem that works in all cases where the mutually exclusive nodes have no common ancestors. Our solution uses a special type of constraint and auxiliary node together with formulas for assigning their necessary conditional probability table values. The solution enforces mutual exclusivity between events and preserves their prior probabilities while leaving all original \BN\ nodes unchanged.
@article{Fenton201639,
Abstract = {Abstract We show that existing Bayesian network (BN) modelling techniques cannot capture the correct intuitive reasoning in the important case when a set of mutually exclusive events need to be modelled as separate nodes instead of states of a single node. A previously proposed `solution', which introduces a simple constraint node that enforces mutual exclusivity, fails to preserve the prior probabilities of the events, while other proposed solutions involve major changes to the original model. We provide a novel and simple solution to this problem that works in all cases where the mutually exclusive nodes have no common ancestors. Our solution uses a special type of constraint and auxiliary node together with formulas for assigning their necessary conditional probability table values. The solution enforces mutual exclusivity between events and preserves their prior probabilities while leaving all original \{BN\} nodes unchanged. },
Author = {Norman Fenton and Martin Neil and David Lagnado and William Marsh and Barbaros Yet and Anthony Constantinou},
Date-Added = {2016-10-24 22:12:29 +0000},
Date-Modified = {2016-11-05 23:32:43 +0000},
Doi = {10.1016/j.knosys.2016.09.012},
Issn = {0950-7051},
Journal = {Knowledge-Based Systems},
Keywords = {Uncertain reasoning},
Pages = {39 - 50},
Title = {How to model mutually exclusive events based on independent causal pathways in Bayesian network models},
Url = {http://www.sciencedirect.com/science/article/pii/S095070511630329X},
Volume = {113},
Year = {2016},
Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/pii/S095070511630329X},
Bdsk-Url-2 = {http://dx.doi.org/10.1016/j.knosys.2016.09.012}}
Downloads: 0
{"_id":"tuMwXvvz3a424LTYh","bibbaseid":"fenton-neil-lagnado-marsh-yet-constantinou-howtomodelmutuallyexclusiveeventsbasedonindependentcausalpathwaysinbayesiannetworkmodels-2016","downloads":0,"creationDate":"2016-11-05T19:47:34.322Z","title":"How to model mutually exclusive events based on independent causal pathways in Bayesian network models","author_short":["Fenton, N.","Neil, M.","Lagnado, D.","Marsh, W.","Yet, B.","Constantinou, A."],"year":2016,"bibtype":"article","biburl":"http://www.eecs.qmul.ac.uk/~william/citations-ref.bib","bibdata":{"bibtype":"article","type":"article","abstract":"Abstract We show that existing Bayesian network (BN) modelling techniques cannot capture the correct intuitive reasoning in the important case when a set of mutually exclusive events need to be modelled as separate nodes instead of states of a single node. A previously proposed `solution', which introduces a simple constraint node that enforces mutual exclusivity, fails to preserve the prior probabilities of the events, while other proposed solutions involve major changes to the original model. We provide a novel and simple solution to this problem that works in all cases where the mutually exclusive nodes have no common ancestors. Our solution uses a special type of constraint and auxiliary node together with formulas for assigning their necessary conditional probability table values. The solution enforces mutual exclusivity between events and preserves their prior probabilities while leaving all original \\BN\\ nodes unchanged. ","author":[{"firstnames":["Norman"],"propositions":[],"lastnames":["Fenton"],"suffixes":[]},{"firstnames":["Martin"],"propositions":[],"lastnames":["Neil"],"suffixes":[]},{"firstnames":["David"],"propositions":[],"lastnames":["Lagnado"],"suffixes":[]},{"firstnames":["William"],"propositions":[],"lastnames":["Marsh"],"suffixes":[]},{"firstnames":["Barbaros"],"propositions":[],"lastnames":["Yet"],"suffixes":[]},{"firstnames":["Anthony"],"propositions":[],"lastnames":["Constantinou"],"suffixes":[]}],"date-added":"2016-10-24 22:12:29 +0000","date-modified":"2016-11-05 23:32:43 +0000","doi":"10.1016/j.knosys.2016.09.012","issn":"0950-7051","journal":"Knowledge-Based Systems","keywords":"Uncertain reasoning","pages":"39 - 50","title":"How to model mutually exclusive events based on independent causal pathways in Bayesian network models","url":"http://www.sciencedirect.com/science/article/pii/S095070511630329X","volume":"113","year":"2016","bdsk-url-1":"http://www.sciencedirect.com/science/article/pii/S095070511630329X","bdsk-url-2":"http://dx.doi.org/10.1016/j.knosys.2016.09.012","bibtex":"@article{Fenton201639,\n\tAbstract = {Abstract We show that existing Bayesian network (BN) modelling techniques cannot capture the correct intuitive reasoning in the important case when a set of mutually exclusive events need to be modelled as separate nodes instead of states of a single node. A previously proposed `solution', which introduces a simple constraint node that enforces mutual exclusivity, fails to preserve the prior probabilities of the events, while other proposed solutions involve major changes to the original model. We provide a novel and simple solution to this problem that works in all cases where the mutually exclusive nodes have no common ancestors. Our solution uses a special type of constraint and auxiliary node together with formulas for assigning their necessary conditional probability table values. The solution enforces mutual exclusivity between events and preserves their prior probabilities while leaving all original \\{BN\\} nodes unchanged. },\n\tAuthor = {Norman Fenton and Martin Neil and David Lagnado and William Marsh and Barbaros Yet and Anthony Constantinou},\n\tDate-Added = {2016-10-24 22:12:29 +0000},\n\tDate-Modified = {2016-11-05 23:32:43 +0000},\n\tDoi = {10.1016/j.knosys.2016.09.012},\n\tIssn = {0950-7051},\n\tJournal = {Knowledge-Based Systems},\n\tKeywords = {Uncertain reasoning},\n\tPages = {39 - 50},\n\tTitle = {How to model mutually exclusive events based on independent causal pathways in Bayesian network models},\n\tUrl = {http://www.sciencedirect.com/science/article/pii/S095070511630329X},\n\tVolume = {113},\n\tYear = {2016},\n\tBdsk-Url-1 = {http://www.sciencedirect.com/science/article/pii/S095070511630329X},\n\tBdsk-Url-2 = {http://dx.doi.org/10.1016/j.knosys.2016.09.012}}\n\n","author_short":["Fenton, N.","Neil, M.","Lagnado, D.","Marsh, W.","Yet, B.","Constantinou, A."],"key":"Fenton201639","id":"Fenton201639","bibbaseid":"fenton-neil-lagnado-marsh-yet-constantinou-howtomodelmutuallyexclusiveeventsbasedonindependentcausalpathwaysinbayesiannetworkmodels-2016","role":"author","urls":{"Paper":"http://www.sciencedirect.com/science/article/pii/S095070511630329X"},"keyword":["Uncertain reasoning"],"metadata":{"authorlinks":{}}},"search_terms":["model","mutually","exclusive","events","based","independent","causal","pathways","bayesian","network","models","fenton","neil","lagnado","marsh","yet","constantinou"],"keywords":["uncertain reasoning"],"authorIDs":[],"dataSources":["PiQLiXZdTfuksxMch"]}