BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Measuring Performance of Likelihood-Ratio-Based Evidence Evaluatio
 n Methods - Daniel Ramos (Universidad Autonoma de Madrid)
DTSTART:20161107T161500Z
DTEND:20161107T170000Z
UID:TALK68841@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:The value of the evidence in forensic science is increasingly 
 expressed by a  Likelihood Ratio (LR)\, following a Bayesian framework. Th
 e LR aims at providing  the information given by the evidence to the decis
 ion process in a trial.  Although theoretical aspects of statistical model
 s are essential to compute the  LR\, in real forensic situations there exi
 st many other factors (including e.g.  data sparsity\, data variability an
 d dataset shift) that might degrade the  performance of the LR. This means
  that the computed LR values might be  misleading\, ultimately causing a l
 oss in the accuracy of the decisions made by  the fact finder. Therefore\,
  it is essential to measure the performance of LR  methods in forensic sit
 uations\, with the further objective of validating LR  methods for its use
  in casework. In this talk\, we will present several popular  performances
  measures for LR values. We will provide examples where these  measures ar
 e used to compare different methods in the context of trace evidence.  Fin
 ally\, we will present a recently-proposed guideline for the validation of
  LR  methods in forensic science\, that relies upon the use of performance
  measures of  LR methods.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR