crime investigation and the criminal trial

1
References 1. Kind SS. Crime investigation and the criminal trial: a three chapter paradigm of evidence. Journal of the Forensic Science Society 1994; 34: 155-164. 2. Aitken CGG. Statistics and the evaluation of evidence for forensic scientists. Chichester: John Wiley & Sons: in press. 3. Lindley DV. Probability. In: Aitken CGG and Stoney DA (eds). The Use of Statistics in Forensic Science. Chichester: Ellis Horwood, 1991: 48. 4. Good IJ. Weight of evidence and the Bayesian likelihood ratio. In: Aitken CGG and Stoney DA (eds). The Use of Statistics in Forensic Science. Chichester: Ellis Horwood, 1991: 85-106. 5. Evett IW and Buckleton JS. Some aspects of the Bayesian approach to evidence evaluation. Journal of the Forensic Science Society 1989; 29: 303-316. 6. Thompson WC and Schumann EL. Interpretation of statistical evidence in criminal trials. The prosecutor's fallacy and the defence attorney's fallacy. Law and Human Behaviour 1987; 11: 167-187. October 1994 CGG AITKEN Department of Mathematics and Statistics University of Edinburgh Mayfield Road, Edinburgh EH9 3JZ Crime investigation and the criminal trial Sir: We have read with concern the article by Dr SS Kind, "Crime investigation and the criminal trial: a three chapter paradigm of evidence", JFSS 1994; 34: 155-164. The important part of the article is an attack on Bayesian reasoning. In the course of this, Dr Kind raises a number of objections which have been much more thoroughly canvassed and, in our view, successfully dealt with, in the literature of the "New Evidence Scholarship". Readers who wish to pursue this discussion are referred to Cardozo Law Review, Vol 13 (1991), Parts 2 & 3 of which are wholly devoted to this subject. For an up to date Bayesian argument and for numerous references may we refer readers to our own article [I] which sets out to refute the philosophic position which Dr Kind has adopted and also many of his detailed points. One issue has recently confused courts in America and so, despite having dealt with it in previous publications, we must mention it now. This is the idea that the assessment of a prior probability conflicts with the presumption of innocence. Two brief responses can be made. Legal text books all agree that the "presumption of innocence" is simply a restatement of the burden and standard of proof. In other words, it is part of the utility calculation, not part of the probability assessment. Assignment of a prior probability of zero is just a formal way of saying "I believe this certainly did not happen and no amount of evidence can change that belief". Any juror who announced this would be disqualified. Reference 1. Robertson BWN and Vignaux GA. Probability-the logic of the law. Oxford Journal of Legal Studies 1993; 13: 457-478. October 1994 BWN ROBERTSON and GA VIGNAUX Wolfson College Oxford OX2 6UD JFSS 1994; 34(4): 268-270

Upload: ga

Post on 14-Jul-2016

228 views

Category:

Documents


3 download

TRANSCRIPT

Page 1: Crime investigation and the criminal trial

References 1. Kind SS. Crime investigation and the criminal trial: a

three chapter paradigm of evidence. Journal of the Forensic Science Society 1994; 34: 155-164.

2. Aitken CGG. Statistics and the evaluation of evidence for forensic scientists. Chichester: John Wiley & Sons: in press.

3. Lindley DV. Probability. In: Aitken CGG and Stoney DA (eds). The Use of Statistics in Forensic Science. Chichester: Ellis Horwood, 1991: 48.

4. Good IJ. Weight of evidence and the Bayesian likelihood ratio. In: Aitken CGG and Stoney DA (eds). The Use of Statistics in Forensic Science. Chichester: Ellis Horwood, 1991: 85-106.

5. Evett IW and Buckleton JS. Some aspects of the Bayesian approach to evidence evaluation. Journal of the Forensic Science Society 1989; 29: 303-316.

6. Thompson WC and Schumann EL. Interpretation of statistical evidence in criminal trials. The prosecutor's fallacy and the defence attorney's fallacy. Law and Human Behaviour 1987; 11: 167-187.

October 1994 CGG AITKEN Department of Mathematics

and Statistics University of Edinburgh Mayfield Road, Edinburgh EH9 3JZ

Crime investigation and the criminal trial

Sir: We have read with concern the article by Dr SS Kind, "Crime investigation and the criminal trial: a three chapter paradigm of evidence", JFSS 1994; 34: 155-164.

The important part of the article is an attack on Bayesian reasoning. In the course of this, Dr Kind raises a number of objections which have been much more thoroughly canvassed and, in our view,

successfully dealt with, in the literature of the "New Evidence Scholarship".

Readers who wish to pursue this discussion are referred to Cardozo Law Review, Vol 13 (1991), Parts 2 & 3 of which are wholly devoted to this subject. For an up to date Bayesian argument and for numerous references may we refer readers to our own article [I] which sets out to refute the philosophic position which Dr Kind has adopted and also many of his detailed points.

One issue has recently confused courts in America and so, despite having dealt with it in previous publications, we must mention it now. This is the idea that the assessment of a prior probability conflicts with the presumption of innocence. Two brief responses can be made.

Legal text books all agree that the "presumption of innocence" is simply a restatement of the burden and standard of proof. In other words, it is part of the utility calculation, not part of the probability assessment.

Assignment of a prior probability of zero is just a formal way of saying "I believe this certainly did not happen and no amount of evidence can change that belief". Any juror who announced this would be disqualified.

Reference 1. Robertson BWN and Vignaux GA. Probability-the

logic of the law. Oxford Journal of Legal Studies 1993; 13: 457-478.

October 1994 BWN ROBERTSON and G A VIGNAUX Wolfson College Oxford OX2 6UD

JFSS 1994; 34(4): 268-270