Bayesian Inference and Forensic Science: Problems and Perspectives

摘要: The debate about whether or not Bayesian inference provides a model for the process of assessing evidence in court law has generated good amount literature and some strongly voiced opinions. Let me start by making my own position clear: I am forensic scientist interested modelling legal only to extent that it enables role scientist's be defined. broader arguments centre on concepts such as odds guilt, but professional colleagues jealously guard their detachment from deliberations guilt otherwise and, personally, reluctant handle equations which contain probabilities. shall concentrate problem evaluating science against two narrower alternatives: C, event suspect was at crime scene scene. great advantage is us identify principle, answer most appropriate range questions should address greatest assistance investigator court. Bayes Theorem shows that, while concerned with type: "what probability scene?", scientist, through likelihood ratio, type given scene?" scene?". While this might appear almost self-evident practising Bayesian, recently scientists have begun converted. Nevertheless there now growing realisation methods something offer optimistic over coming years we can do lot fan small flame. propose next describe essentials transfer problem; then briefly work been done so far developing solutions; look ways developments could take place here, emphasising major challenges are faced.