TY - JOUR
T1 - Assessing the statistical reliability of witness evidence
AU - Croucher, John S.
N1 - Copyright LexisNexis and the Author(s). Version archived for private and non-commercial use with the permission of the publisher and the author(s). For further reproduction rights please contact the publisher at http://www.lexisnexis.com.au.
PY - 2003
Y1 - 2003
N2 - As Professor Croucher gently reminds us, the theory of probability is widely misunderstood by most members of the general public so it comes as no surprise that it also poses a real challenge to legal practitioners. This has led to erroneous conclusions ‘based on the evidence’ that have become known as a variety of ‘fallacies’, including those of both the prosecutor and defence. Whether or not the underlying mathematics is fully understood, it is essential that practitioners can correctly interpret the information provided by witnesses, expert or otherwise. This article provides one contribution in that direction. It presents an easy to understand set of tables that can be readily used to determine the likelihood that a statement made by a witness is actually true from a statistical point of view. Although the relevant statistical arguments are provided, the answers can be found in most cases without resorting to any calculations whatsoever.
In the promotional blurb for the second edition of Sir Richard Eggleston’s classic Evidence, Proof and Probability (1983) Sir Richard was described as ‘the first lawyer to describe systematically the central role played by probability in fact-finding’. Whether or not that was too bold a claim, he was not the last lawyer to address the topic. It has attracted many practising and academic lawyers. The well known paper of Justice D H Hodgson, (‘The Scales of Justice:Probability and Proof in Legal Fact-Finding’ (1995) 69 ALJ 731) demonstrates the continuing interest in the topic at the highest levels of the legal profession. In this article Professor Croucher, of the Department of Statistics at Macquarie University in Sydney, offers practical guidance informed by mathematical training and insight.
AB - As Professor Croucher gently reminds us, the theory of probability is widely misunderstood by most members of the general public so it comes as no surprise that it also poses a real challenge to legal practitioners. This has led to erroneous conclusions ‘based on the evidence’ that have become known as a variety of ‘fallacies’, including those of both the prosecutor and defence. Whether or not the underlying mathematics is fully understood, it is essential that practitioners can correctly interpret the information provided by witnesses, expert or otherwise. This article provides one contribution in that direction. It presents an easy to understand set of tables that can be readily used to determine the likelihood that a statement made by a witness is actually true from a statistical point of view. Although the relevant statistical arguments are provided, the answers can be found in most cases without resorting to any calculations whatsoever.
In the promotional blurb for the second edition of Sir Richard Eggleston’s classic Evidence, Proof and Probability (1983) Sir Richard was described as ‘the first lawyer to describe systematically the central role played by probability in fact-finding’. Whether or not that was too bold a claim, he was not the last lawyer to address the topic. It has attracted many practising and academic lawyers. The well known paper of Justice D H Hodgson, (‘The Scales of Justice:Probability and Proof in Legal Fact-Finding’ (1995) 69 ALJ 731) demonstrates the continuing interest in the topic at the highest levels of the legal profession. In this article Professor Croucher, of the Department of Statistics at Macquarie University in Sydney, offers practical guidance informed by mathematical training and insight.
M3 - Article
VL - 23
SP - 173
EP - 183
JO - Australian Bar Review
JF - Australian Bar Review
SN - 0814-8589
IS - 2
ER -