Modeling crime events by d-separation method
R Aarthee,D Ezhilmaran +1 more
- Vol. 263, Iss: 4, pp 042145
TLDR
This work proposes a d-separation method for modeling the crime events that aims to lay the foundations for the development of a software support tool that can deal with the evidential reasoning in legal cases.Abstract:
Problematic legal cases have recently called for a scientifically founded method of dealing with the qualitative and quantitative roles of evidence in a case [1].To deal with quantitative, we proposed a d-separation method for modeling the crime events. A d-separation is a graphical criterion for identifying independence in a directed acyclic graph. By developing a d-separation method, we aim to lay the foundations for the development of a software support tool that can deal with the evidential reasoning in legal cases. Such a tool is meant to be used by a judge or juror, in alliance with various experts who can provide information about the details. This will hopefully improve the communication between judges or jurors and experts. The proposed method used to uncover more valid independencies than any other graphical criterion.read more
References
More filters
Book ChapterDOI
On the logic of causal models
Dan Geiger,Judea Pearl +1 more
TL;DR: In this paper, the role of directed cyclic graphs (DAGs) as a representation of conditional independence relationships is explored, and it is shown that DAGs offer polynomially sound and complete inference mechanisms for inferring conditional independence relationship from a given causal set of such relationships.
Journal ArticleDOI
Pearl's D-Separation: One More Step Into Causal Thinking
Leslie A. Hayduk,Greta G. Cummings,Rainer F. Stratkotter,Melanie Nimmo,Kostyantyn Grygoryev,Donna Dosman,Michael Gillespie,Hannah Pazderka-Robinson,Kwame Boadu +8 more
TL;DR: This paper provided a relatively accessible entry into the causal structural equation modeling literature, and made substantial progress toward elucidating a logical structure capable of distinguishing evidence-supported causal claims from unsupported SEM causal claims.
Posted Content
On the Logic of Causal Models
Dan Geiger,Judea Pearl +1 more
TL;DR: It is shown that DAGs offer polynomially sound and complete inference mechanisms for inferring conditional independence relationships from a given causal set of such relationships, and d-separation, a graphical criterion for identifying independencies in a DAG, is shown to uncover more valid independencies then any other criterion.