The Eighth International Conference on Forensic Inference and Statistics

The Eighth International Conference on Forensic Inference and Statistics was held at The University of Washington, Seattle, USA, in July 2011, under the Chairmanship of Professor Bruce Weir. The conference was preceded by a day in which there were three short courses on Probabilistic Reasoning for Judges and Lawyers, Statistical Methods for DNA Evidence and Bayesian Networks in Forensic Science. The conference itself had a varied programme including sessions on the anthrax letter mailings, discrimination, DNA, individualization, plagiarism, trace evidence, as well as a discussion session involving four distinguished judges from the USA and Canada. Four papers developed from presentations at the conference are published here. David Kaye draws comparisons between the so-called birthday problem and source attribution and individualization in forensic science testimony. In its simplest form, the birthday problem is this: assuming that everyone is equally likely to be born on any day of the year (assuming it is not a leap year), how many people must enter a room for the probability that it contains at least one pair of individuals born on the same day of the same month is greater than 0.5? The answer is 23, an answer which appears much lower than intuition suggests. The relationship of this result to individualization is the theme of the paper. Weiwen Miao and Joe Gastwirth consider an example in civil law with a study of the properties of statistical tests appropriate for the analysis of data in disparate impact cases. The paper reviews the use of statistical tests to establish a prima facie case that an examination has a disparate impact on minorities. Two common scenarios are discussed. The first is that promotions are made in accordance with the rank-order of the exam scores or a composite of the exam scores and some other factors. The second situation occurs when once an applicant passes the exam, they are eligible for further consideration for promotion. The actual exam score no longer matters. Courts may need to consider the practical significance of the observed difference in pass rates and the power of the test of detecting a legally important difference. Qing Pan and Joe Gastwirth consider another example in civil law with a study on the appropriateness of survival analysis for determining lost pay in discrimination cases when the number of plaintiffs exceeds the number of job openings. The ideas are illustrated with an application of the ‘Lost Chance’ doctrine to Alexander v. Milwaukee, 474 F.3d. 437 (7th Cir. 2007). In equal employment cases concerning fair hiring or promotion, the number of eligible applicants often exceeds the number of available positions. When a group of plaintiffs show that they were discriminated against in the selection process, one cannot determine with certainty which ones would have been chosen. Several decisions from the Seventh Circuit observed that this situation is similar to the loss of a chance in tort law where due to negligence the survival probability of a patient has been diminished. In both settings the plaintiff’s loss can be regarded as probabilistic, i.e. in the discrimination context they lost their chance of obtaining the job. This paper shows how methods of survival analysis provide statistically sound estimates of the compensation due to a plaintiff. By the very nature of its topic, the underlying philosophy of the conference is Bayesian. However, Michael Risinger ensured that the conference was not one of mutual admiration in a paper entitled ‘Some reservations about likelihood ratios (and some aspects of forensic “Bayesianism”)’. Current Bayesian orthodoxy in forensic science raises concerns with Risinger. He explains that [Bayesian orthodoxy] may in some circumstances not be fit for purpose, at least as the details are currently conceived, in the context of criminal law enforcement and the jury trial. He has various objections to the Bayesian approach. These include the practice in the UK of referring to the propositions used in the formation of the likelihood ratio as those of the prosecution and of the defence and of the use of levels of proposition such as the activity level. For those of us, including this author, who support the ideas to which Risinger objects, his strictures are a reminder that there are many people out there for whom much work is still to be done to persuade them of the error of their ways! This triennial conference started in Edinburgh in 1990 under the title of ‘Forensic Statistics’. Much has happened in forensic science and the evaluation and interpretation of evidence in the intervening 22 years. The Royal Statistical Society has formed a Statistics and Law working group, the American Statistical Association has formed an ad hoc committee on Forensic Science, and influential reports such as the National Research Council of the USA Strengthening Forensic Science in the United States: A Path Forward (2009) and the Law Commission of England and Wales (2011) Expert Evidence in Criminal Proceedings in England and Wales (Law Com 325) have supported the need for an increased use of statistics and probabilistic reasoning in the criminal courts. Not least, this journal is now entering its 12th year. The conference is more important than ever as a unique forum in which lawyers, forensic scientists and statisticians come together to discuss topics of current interest. It next meets in 2014 in The Hague under the organization of The Netherlands Forensic Institute.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.