University of Lausanne, School of Criminal Justice, Lausanne, Switzerland.
Forensic Sci Int. 2012 Jan 10;214(1-3):189-94. doi: 10.1016/j.forsciint.2011.08.007. Epub 2011 Sep 9.
This paper extends previous research and discussion on the use of multivariate continuous data, which are about to become more prevalent in forensic science. As an illustrative example, attention is drawn here on the area of comparative handwriting examinations. Multivariate continuous data can be obtained in this field by analysing the contour shape of loop characters through Fourier analysis. This methodology, based on existing research in this area, allows one describe in detail the morphology of character contours throughout a set of variables. This paper uses data collected from female and male writers to conduct a comparative analysis of likelihood ratio based evidence assessment procedures in both, evaluative and investigative proceedings. While the use of likelihood ratios in the former situation is now rather well established (typically, in order to discriminate between propositions of authorship of a given individual versus another, unknown individual), focus on the investigative setting still remains rather beyond considerations in practice. This paper seeks to highlight that investigative settings, too, can represent an area of application for which the likelihood ratio can offer a logical support. As an example, the inference of gender of the writer of an incriminated handwritten text is forwarded, analysed and discussed in this paper. The more general viewpoint according to which likelihood ratio analyses can be helpful for investigative proceedings is supported here through various simulations. These offer a characterisation of the robustness of the proposed likelihood ratio methodology.
本文扩展了之前关于多元连续数据的使用的研究和讨论，这些数据即将在法医学领域得到更广泛的应用。本文以比较笔迹检验领域为例，通过傅里叶分析对连笔字符的轮廓形状进行分析，从而获得该领域的多元连续数据。这种基于该领域现有研究的方法可以详细描述字符轮廓在一系列变量中的形态。本文使用从女性和男性书写者那里收集的数据，对评估和调查程序中的基于似然比的证据评估程序进行了比较分析。虽然在评估性程序中使用似然比的做法现在已经相当成熟（通常用于区分给定个体与其他未知个体的书写主张），但在实践中，对调查性程序的关注仍然远远不够。本文旨在强调，调查性程序也可以是似然比可以提供逻辑支持的应用领域之一。例如，本文提出、分析和讨论了推断手写案文作者的性别这一案例。本文通过各种模拟支持了似然比分析有助于调查性程序的更普遍观点。这些模拟提供了对所提出的似然比方法的稳健性的描述。
