O'Reilly logo

Bayesian Networks for Probabilistic Inference and Decision Analysis in Forensic Science, 2nd Edition by Colin Aitken, Paolo Garbolino, Silvia Bozza, Alex Biedermann, Franco Taroni

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

7.5 Interpretation with more than two propositions

Consider again a situation in which the finding E consists of a DNA profile of a stain of body fluid found at a crime scene and of the DNA profile of a suspect that corresponds, in some sense, to that of the crime stain. Until now, such scenarios have been evaluated with respect to pairs of propositions H, introduced in Section 7.1. At source level, these are, typically, the suspect is the source of the crime stain (c07-math-0728) and another person, unrelated to the suspect, left the crime stain (c07-math-0729).

However, it may well be that the relevant population contains close relatives of the suspect. It is important to account for this possibility, as argued by Buckleton and Triggs (2005), since close relatives are far more likely to have corresponding genetic traits than other members of the population. The defence may thus require forensic scientists to incorporate in their analysis more than one proposition. An approach for such a situation, using posterior probabilities, has been discussed by Evett (1992). It considers the following three propositions: ‘The suspect left the crime stain (c07-math-0730)’, ‘An unknown member of the population left the crime stain ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required