skip navigation


Register for Latest Research

Stay Informed
Register with NCJRS to receive NCJRS's biweekly e-newsletter JUSTINFO and additional periodic emails from NCJRS and the NCJRS federal sponsors that highlight the latest research published or sponsored by the Office of Justice Programs.

NCJRS Abstract

The document referenced below is part of the NCJRS Virtual Library collection. To conduct further searches of the collection, visit the Virtual Library. See the Obtain Documents page for direction on how to access resources online, via mail, through interlibrary loans, or in a local library.


NCJ Number: 134751 Find in a Library
Title: Who is "Random Man"?
Journal: Journal of the Forensic Science Society  Volume:31  Issue:4  Dated:(October/December 1991)  Pages:463-468
Author(s): J S Buckleton; Walsh K; I Evett
Date Published: 1991
Page Count: 6
Type: Research (Theoretical)
Format: Article
Language: English
Country: United Kingdom
Annotation: The application of Bayesian inference to the evaluation of forensic evidence is discussed with a focus on selection of survey data.
Abstract: Bayes' theorem deals with the ratio of two probabilities: the conditional probability of the evidence calculated under the assumption that the suspect did commit the crime divided by the conditional probability of the evidence calculated under the assumption that the suspect did not commit the crime. In order to understand the probability of the evidence under the latter assumption, a survey of people unassociated with the crime is warranted. In many instances, such survey data are already available. The dilemma arises with the choice of a particular population. A survey should be representative of all possible offenders using background information such as race, nature, or lifestyle of the suspect only if relevant to the case. In cases where there is a transfer from the offender to the scene, the race, nature, or lifestyle of the suspect do not influence thinking on which population to choose because the suspect details are irrelevant. However, data developed from previous cases should not be dismissed and may prove useful in cases where the transfer was from the scene to the suspect. In these cases, the nature and lifestyle of the suspect condition the thinking about selection of population type. 6 references
Main Term(s): Forensic sciences; Probabilistic evidence; Sampling
Index Term(s): Crime surveys; Data collections
To cite this abstract, use the following link:

*A link to the full-text document is provided whenever possible. For documents not available online, a link to the publisher's website is provided. Tell us how you use the NCJRS Library and Abstracts Database - send us your feedback.