DocumentCode :
1252156
Title :
Probabilistic relevance relations
Author :
Geiger, Dan ; Heckerman, David
Author_Institution :
Microsoft Corp., Redmond, WA, USA
Volume :
28
Issue :
1
fYear :
1998
fDate :
1/1/1998 12:00:00 AM
Firstpage :
17
Lastpage :
25
Abstract :
The intuition behind the construction of Bayesian networks and other graph-based representations of joint probability distributions from expert judgments is based on the assumed relationship between “connectedness” in the graphical model and “relatedness” among the variables involved. We show that several plausible definitions of relatedness do not adhere to such an equivalence. We then provide a definition of probabilistic relatedness that is closely related to connectedness in the graphical model and prove that the two concepts are equivalent whenever the model uses only propositional variables and assuming every combination of value assignment to these variables is feasible. We conjecture that the equivalence established holds also when these restrictions are lifted
Keywords :
directed graphs; probability; set theory; Bayesian networks; connectedness; expert judgments; graph-based representations; joint probability distributions; probabilistic relatedness; probabilistic relevance relations; relatedness; value assignment; Bayesian methods; Computer science; Concrete; Databases; Graphical models; Humans; Probability distribution; Random variables;
fLanguage :
English
Journal_Title :
Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on
Publisher :
ieee
ISSN :
1083-4427
Type :
jour
DOI :
10.1109/3468.650318
Filename :
650318
Link To Document :
بازگشت