Law, Probability and Risk - current issue

Rotationally invariant statistics for examining the evidence from the pores in fingerprints

Parsons, N. R., Smith, J. Q., Thonnes, E., Wang, L, Wilson, R. — 2008-02-22

Recent methodological advances in the processing of DNA evidence have begun to force a closer examination of assertions about the strength of other sorts of evidence. One traditional source of evidence is the fingerprint. Currently a print taken from a suspect is compared against a mark from a crime scene and a match declared using the judgement of an expert based on matching minutiae and the ridge patterns around these. However, such methods have proved difficult to quantify effectively. This has provoked the investigation of even finer features in the print and the mark. One set of such features are the many pores, located along the ridges of the fingerprint. Is it possible to supplement expert judgements associated with a match with a more automatic and quantitative measure of the strength of evidence, based on pore information? The results of this preliminary analysis suggest we can. Our methodology is relatively transparent, using common statistics for two sample comparisons of point patterns. The results discussed here concern the matching of inked prints using grey-level imaging and complement previous studies which tend to focus on the comparison of binarised images.

The role of epidemiology in the law: a toxic tort litigation case

Dominici, F., Kramer, S., Zambelli-Weiner, A. — 2008-02-22

Toxic tort cases provide a natural framework for an in-depth illustration and an application of statistical methods for small-scale studies of putative sources of hazard. In this paper, we describe the aspects of a toxic tort case that focussed on quantifying the strength of evidence concerning the hypothesis that carcinogenic substances emitted from an industry source were associated with a statistically significant higher than expected incidence rate of neuroblastoma in children. We first present the epidemiological analysis carried out by the plaintiffs' experts (Drs P1, P2 and P3). We then summarize the key critiques by the defense experts (Drs D1, D2 and D3) followed by the plaintiff's reply. In the context of toxic torts, the plaintiff must demonstrate that the exposure resulting from the defendants' conduct is more likely than not causally related to the injury. We use this toxic tort case to identify common criticisms of the defense experts that take advantage of the complexity in evaluating causation in toxic torts. In the discussion, we summarize the common defense positions and question whether such questions are scientifically appropriate.

Analysis of sampling issues using Bayesian networks

Biedermann, A., Taroni, F., Bozza, S., Aitken, C. G. G. — 2008-02-22

This paper addresses the implementation of Bayesian sampling methodology in a graphical probability environment, i.e. Bayesian networks (BNs). An architecture of BNs which is able to be used for sampling from small and large consignments is outlined in detail. Through direct interaction with their users, the proposed models provide a framework that is capable of dealing with several distinct sampling issues, such as (i) the calculation of posterior probability distributions for the proportion of ‘positives’ (i.e. discrete units with a characteristic of interest) in a consignment as well as for the number of positives among a consignment's uninspected items, (ii) case preassessment and (iii) likelihood-ratio evaluation. A discussion is included on features of the proposed models that allow one to account for further complications such as competing prior beliefs about the proportion of positives in a consignment and potentially misclassified data (e.g. positive testing results obtained from units that are actually negative).

Case comment: an expert's report criticizing plaintiff's failure to account for multiple comparisons is deemed admissible in EEOC v.Autozone

Gastwirth, J. L. — 2008-02-22

In its opinions in Daubert, Joiner and Kumho Tire, the U.S. Supreme Court assigned trial judges a ‘gate-keeping’ role in assuring that proposed expert testimony is sufficiently reliable that it should be admitted into evidence. A section of the Daubert decision described guidelines to assist trial judges in their evaluation of expert testimony. This comment discusses a careful district court opinion concerning a motion, under the principles of Daubert, to exclude the report of defendant's expert in the sex discrimination case, EEOC v. Autozone. The technical statistical issue dealt with the need for adjusting the observed significance levels or p-values of individual statistical tests when a large number of related tests are conducted. The Equal Employment Opportunity Commission and its expert argued that while such adjustments are used in medical applications of statistics, they are not needed in labour economics. The decision is noteworthy because the judge realized that the principles of statistical inference remain the same regardless of the origin of the data. After describing the issue and reanalysing some of the data, alternative statistical methods that stratify the data into comparable subgroups and combine the results for the separate strata are often more appropriate. They avoid making many separate tests and have higher statistical power to detect discrimination. Since 10 years of hiring and promotion data were analysed, which cover both pre- and post-charge time periods, two possible scenarios are described. The first is the one that apparently was the focus of both experts and the second focuses on the status of a particular female plaintiff for a job as guard in the early period. It is shown that overall the data do not support a claim of class-wide discrimination but might support a claim of sex discrimination in hiring for guard positions in the pre-charge time period.

Expert Evidence and Criminal Justice, by Mike Redmayne

Lucy, D. — 2008-02-22

Genetic Testing and the Criminal Law, by Don Chalmers

Fordham, J. — 2008-02-22

Reliability and Risk: A Bayesian Perspective, by Nozer Singpurwalla

Lee, P. M. — 2008-02-22