University of Technology Sydney

# 35255 Forensic Statistics

Warning: The information on this page is indicative. The subject outline for a particular session, location and mode of offering is the authoritative source of all information about the subject for that offering. Required texts, recommended texts and references in particular are likely to change. Students will be provided with a subject outline once they enrol in the subject.

Subject handbook information prior to 2021 is available in the Archives.

UTS: Science: Mathematical and Physical Sciences
Credit points: 6 cp

There are course requisites for this subject. See access conditions.

### Description

This subject provides students with an understanding of the role of probabilistic inference in forensic science and interpretation of the fundamental unit of forensic science, 'the trace'. Students gain skills in using the logical approach to interpret observations and results in the context of practical forensic examples, case studies, and databases of forensic data. This subject aims to provide students with foundational knowledge in forensically relevant probability theory, statistical analysis and modelling methods to prepare them for subsequent subjects and apply to their specific area of expertise.

### Subject learning objectives (SLOs)

Upon successful completion of this subject students should be able to:

1. Understand the role of propositions and inference in forensic science Apply probability theory to the interpretation of traces Evaluate the value of traces in a wide range of scenarios encountered in forensic science (including source level and activity level questions, database hits, and multiple traces) Explain the value of the evidence in verbal and written forms Analyse and visualise data using the R coding language

### Course intended learning outcomes (CILOs)

This subject also contributes specifically to the development of following course intended learning outcomes:

• Analyse: Evaluate the collection of traces and interpret the results of analyses through the use of propositions, hypotheses, and statistical methods. (1.2)
• Apply: Employ investigative and problem-solving skills to evaluate forensic science problems. (2.1)
• Analyse: Combine various methods to record and communicate observations and evaluation of traces throughout all stages of an investigation. (5.2)

### Contribution to the development of graduate attributes

Forensic Statistics is a foundational subject within the forensic science degree program at UTS. Skills learnt in this subject will be applied throughout the remainder of the course and are key to graduate success. Students are introduced to the problem-solving, scientific and communication skills required in a professional context. Upon completion of this subject, students should be able to assign appropriate evidential weight to various types of traces in the context of cases typically encountered in forensic science.

Graduate Attribute 1 – Disciplinary Knowledge

Students will develop a working knowledge of forensic science practice, evaluation of traces and integration of the derived information with the investigative and legal systems in the lectures and workshops. Students will learn how to formulate an appropriate pair of propositions based on the case circumstances, assess the probability of the findings given a proposition for multiple types of traces, and present the weight of evidence in a logical and transparent manner. This will be assessed in assessment tasks 1 and 3.

Graduate Attribute 2 – Research, Inquiry and Critical Thinking

Students will investigate case examples in the tutorial activities and engage in group activities to solve trace evaluation problems using knowledge drawn from the lectures, computer labs and from self-directed learning activities. This will be assessed in all three assessment tasks.

Students will be introduced to the skills required for professional-level communication in forensic science. Students will learn and be assessed on their oral and written communication skills in the presentation of probabilistic information. Students will be able to develop their oral communication skills during the computer labs where there will be opportunities for them to present their findings where they can receive informal feedback. Students written communication skills will be assessed in assessment tasks 2 and 3.

### Teaching and learning strategies

This subject will be delivered through lectures, computer labs, workshops and independent learning activities.

Lectures

There will be 2 hours of lectures each week. These sessions introduce and explain key principles in forensic statistics and relate them to modern professional practice. The lectures also offer opportunities for questions and clarification of subject material. Attendance is recommended at all lectures to develop a complete understanding of the content. Students should read the relevant reading material provided on UTSOnline, as this will prepare the students for active discussion in class. All resources used in the lectures will be available through UTSOnline before the scheduled classes, allowing students to concentrate on and contribute to the discussion in class. Case studies are integrated extensively throughout the lectures to provide a context for the theory being presented.

Computer Labs

The computer labs are an essential part of the subject as they will consolidate a student's understanding of concepts delivered in the lectures. Students will work in groups to solve problems and will be required to present their results verbally to the class and in written form. These will be followed by class discussions and oral feedback. More specifically, computer lab activities will include learning and exploring the use of RStudio for solving problems, an introduction to data analysis, and producing graphs to visually represent specific aspects of a dataset. Attendance for the computer lab program is compulsory and assessed through two graded assessment tasks conducted in groups (see Assessment Tasks 2 and 3). Written feedback will be given to each group for each of these assessment tasks.

Workshops

The workshops are an opportunity for students to engage in in-depth discussions of topics presented in lectures, obtain additional explanations on these topics, and explore the interpretation of evidence in mock case scenarios. More specifically, workshop activities will include studying case scenarios, assessing expert witness statements, and evaluating forensic results for various types of traces in mock case scenarios.

Independent Learning Activities

Independent learning activities with structured feedback are employed in Forensic Statistics, accessed through UTSOnline. These take the form of self-directed online activities. These online activities accompany the lectures throughout the semester to provide students with learning opportunities and individual feedback prior to the larger assessment activities. The online activities contain compulsory exercises that are formally assessed, and contribute to the student’s final grade. After the submission deadline, the student will be able to see which exercises they got right or wrong, and this will give them individual feedback on how well they understood each topic.

An aim of this subject is to help you develop academic and professional language and communication skills to succeed at university and in the workplace. During the course of this subject, you will complete a milestone assessment task that will, in addition to assessing your subject-specific learning objectives, assess your English language proficiency.

### Content (topics)

• Inference in forensic science. Introduction to probability theory, laws of probability, conditional probability, Bayes’ theorem (probabilities), reasoning processes.
• Weight of evidence. Match probability, likelihood ratio, Bayes’ theorem (odds), working with Bayes’ theorem, reporting a likelihood ratio. Transposed conditional, prosecutor’s fallacy, defence attorney’s fallacy, uniqueness fallacy.
• Hierarchy of propositions. Source, activity and offense level propositions and evidence assessment.
• Evidence assessment at the activity level. Likelihood ratios, transfer probabilities, background probabilities. Evaluation of glass evidence. Evaluation of fibre evidence.
• Evidence assessment at the offense level. Likelihood ratios, relevance of a trace, relationship between offense and source level propositions, combining evidence.
• Formulating propositions. Propositions and explanations, defining the relevant population.
• Evidence assessment for combining evidence. Likelihood ratio, two-trace problem, database search problem.
• Introduction to forensic genetics. Concepts of population genetics, Hardy-Weinberg equilibrium, linkage equilibrium, population genetic models. Validation of population genetic models, independence tests, Fisher's exact test, Bonferonni correction.
• Validation of forensic methods. Discrimination, misleading evidence, performance, calibration, Tippett plots.
• Introduction to Bayesian networks (BNs). Definition of BNs, propagation of uncertainty in a BN, fundamental types of connections. Fundamental structures for evidence assessment at source, activity and offense levels.

### Assessment

#### Assessment task 1: Independent Learning Activities

Intent: This assessment task contributes to the following graduate attributes: 1. Disciplinary Knowledge 2. Research, Inquiry and Critical Thinking This assessment task addresses subject learning objective(s): 1, 2 and 3 This assessment task contributes to the development of course intended learning outcome(s): 1.2 and 2.1 Quiz/test Individual 40% correct choice of reasoning; correct application of knowledge and techniques of forensic statistics; correct choice of problem solving strategies and procedures.

#### Assessment task 2: RStudio Data Analysis

Intent: This assessment task contributes to the following graduate attributes: 2. Research, Inquiry and Critical Thinking 5. Communication This assessment task addresses subject learning objective(s): 4 and 5 This assessment task contributes to the development of course intended learning outcome(s): 2.1 and 5.2 Report Group, group and individually assessed 25% correctness of the answers to the questions clarity, quality and correctness of the R code quality of R output files (e.g., graphs generated in R) correct application of appropriate data analysis techniques contribution to the group report

#### Assessment task 3: Evaluation of Evidence Report

Intent: This assessment task contributes to the following graduate attributes: 1. Disciplinary Knowledge 2. Research, Inquiry and Critical Thinking 5. Communication This assessment task addresses subject learning objective(s): 1, 2, 3 and 4 This assessment task contributes to the development of course intended learning outcome(s): 1.2, 2.1 and 5.2 Report Group, group and individually assessed 35% Students will be assessed based on: correct use of language and structure for writing a report appropriateness of the pair of propositions correctness of formulae used for assigning the likelihood ratio correctness of numerical calculations performed for assigning the likelihood ratio clarity and quality of written statements expressing and explaining the degree of support for one proposition with regard to the alternative proposition contribution to the group in the groupwork part of this task

### Minimum requirements

A student must obtain at least 40% of the marks available for Assessment Task 1 in order to pass this subject. If 40% is not reached, an X (fail) grade will be awarded for the subject, irrespective of an overall mark greater than 50. In addition, students must receive at least 50% overall.

A student should demonstrate competence in all aspects of the assessment in order to pass the subject. To pass the subject, a student must achieve a final result of 50% or more. The final result is simply the sum of the marks gained in each piece of assessment.

### Required texts

Each week has a mandatory reading assignment. These assignments include relevant excerpts from the recommended texts and other resources listed in the sections below. PDF files of the required texts will be made available each week on UTSOnline under "Subject Documents".

### Recommended texts

B. Robertson, G.A. Vignaux, C.E.H. Berger. Interpreting Evidence. John Wiley & Sons, Chichester, 2nd edition, 2016, ISBN 9781118492482.

C.G.G. Aitken, P. Roberts, G. Jackson. Practitioner Guide No. 1: Fundamentals of Probability and Statistical Evidence in Criminal Proceedings. Royal Statistical Society, 2010. (full text available on UTSOnline under "Books")

C.G.G. Aitken and F. Taroni. Statistics and the Evaluation of Evidence for Forensic Scientists. John Wiley & Sons, Chichester, 2nd edition, 2004, ISBN 0-470-84367-5.

D.V. Lindley. Understanding Uncertainty. John Wiley & Sons, Chichester, 2nd edition, 2013, ISBN 9781118650127.

### Other resources

J.S. Buckleton, J.-A. Bright, D. Taylor. Forensic DNA Evidence Interpretation. CRC Press, Boca Raton, 2nd edition, 2016, ISBN 9781482258899.

J.M. Curran. Introduction to Data Analysis with R for Forensic Scientists. CRC Press, Boca Raton, 2011, ISBN 978-1-4200-8826-7.

P. Roberts, C.G.G. Aitken. Practitioner Guide No. 3: The Logic of Forensic Proof: Inferential Reasoning in Criminal Evidence and Forensic Science. Royal Statistical Society, 2014.

F. Taroni, C.G.G. Aitken, P. Garbolino, A. Biedermann. Bayesian Networks and Probabilistic Inference in Forensic Science. John Wiley & Sons, Chichester, 2006, ISBN 9780470091739.

F. Taroni, A. Biedermann, S. Bozza, P. Garbolino, C.G.G. Aitken. Bayesian Networks for Probabilistic Inference and Decision Analysis in Forensic Science. John Wiley & Sons, Chichester, 2nd edition, 2014, ISBN 9780470979730.

F. Taroni, S. Bozza, A. Biedermann, P. Garbolino, C.G.G. Aitken. Data Analysis in Forensic Science: A Bayesian Decision Perspective. John Wiley & Sons, Chichester, 2010, ISBN 9780470998359.