60117 Understanding Data and Statistical Design
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 2024 is available in the Archives.
Credit points: 6 cp
Result type: Grade and marks
There are course requisites for this subject. See access conditions.
Anti-requisite(s): 37012 Understanding Data: Making Population Statements with Samples AND 37013 Understanding Data: Linear Regression Models for Interpretation and Prediction AND 37014 Understanding Data: Statistical Models for Binary Outcomes AND 60902 The Scientific Method
Description
The ability to apply experimental methods to a diverse range of scientific applications is an essential capability for all those pursuing a career in science. This subject provides students with a logical framework for conducting and assessing scientific research, from applying statistical tools to experimental data to drawing inferences and conclusions from this analysis. Students gain an understanding of how hypotheses are defined for testing, how adequate sample size can be determined and how data can be analysed and modelled. An introduction to the concept of uncertainty, as relating to scientific experimentation, is also covered, as is a brief discussion of ethics as relating to statistical practice. This subject aims to impart an understanding of the concept of the 'scientific method', necessary for all students destined for a research, research management, research training or other science-oriented career.
Subject learning objectives (SLOs)
Upon successful completion of this subject students should be able to:
| 1. | formulate relevant hypotheses and design appropriate experiments and data collection plans to test those hypotheses |
|---|---|
| 2. | apply univariate and multivariate statistical data analysis methodology to hypothesis testing and experimentation |
| 3. | implement statistical analysis methodology in R programming language |
| 4. | communicate analysis results and conclusions clearly and write critical reports assessing papers and journal articles |
Course intended learning outcomes (CILOs)
This subject also contributes specifically to the development of following course intended learning outcomes:
- Demonstrate critical engagement with the appraisal of advanced knowledge and demonstrate advanced application of knowledge and technical skills to conduct research and generate new knowledge relevant to professional practice in science. (1.1)
- Assess, argue for, and conduct appropriate approaches to independent research and solving complex problems and apply a research methodology to address a research need in a relevant professional context. (2.1)
- Develop, prepare, and engage, at times collaboratively, in work practices that demonstrate an understanding of health and safety requirements, ethical conduct, risk management, organisation, record keeping and collaborative skills in the context of science. (3.1)
- Present and communicate complex ideas and justifications using appropriate communication approaches from a variety of methods (oral, written, visual) to communicate with discipline experts, scientists, industry, and the general public. (5.1)
Contribution to the development of graduate attributes
This subject contributes to the development of the following graduate attributes:
1. Disciplinary knowledge
Knowledge of statistics to demonstrate depth, breadth, application, and interrelationships of relevant discipline areas.
2. Research, inquiry and critical thinking
The ability to frame conjectures and hypotheses using a scientific approach, to test current statistics knowledge through critical evaluation and data analyses, and to solve problems through theoretical work and/or experimental observation.
3. Professional, ethical and social responsibility
A capacity to work ethically and professionally using technical, practical, and collaborative statistics skills within the context of the workplace, and apply these to meet the current and future needs of society.
5. Communication
Effective and professional communication skills for a range of scientific audiences.
Teaching and learning strategies
This subject is taught with a two hour lecture and a one-and-a-half hour PC laboratory session each week. In these classes, students will learn, practise and ask questions and discuss the application of relevant statistical analyses to test hypotheses and address research questions.
Before the first week of class, students are expected to familiarise themselves with Canvas. The subject outline, theoretical material, lab problems, assignment questions and other material will be made available through Canvas.
The lectures comprise a mixture of theory, essential for such a complex and technical field such as statistics, and practical examples where the principles of experiment design and statistical methodology are combined to analyse scientific problems. Time will be allocated in each lecture to review solutions to the previous week's lab work, with this session structured as an informal Q&A. As part of this, students will present their own solutions to lab problems and will be expected to answer any questions arising from their presentations. Verbal feedback on these presentations will be provided by the lecturer.
The laboratory sessions themselves will be conducted in a computer lab where data from actual experiments will be analysed using the programming language R. Students will be encouraged to work collaboratively in the labs but will be expected to complete their lab reports individually. These labs will be informal in nature, with students encouraged to ask questions about the set lab work. Submitted lab work will be returned to students the following week complete with written feedback, suggesting ways in which their analysis may be improved.
Because the subject content builds cumulatively, as preparation for each lecture students must have learnt the material from the preceding lecture. The topic of each week’s lab will be based on the content of that week’s lecture, illustrating the necessity for students to have learnt the theoretical material and to have also completed the lab work from the preceding week.
In Week 1 the lecturer will provide details of consultation times, during which students may request assistance that could not be provided during formal class sessions. Questions may also be asked via email (address listed at top of document), with responses to be provided within two working days.
Content (topics)
The following topics will be covered:
- Review of statistics and data types.
- Elements of experiment design: experimental units, factors, levels, treatments, blocks and interaction.
- Types of experiments: single-factor, two-factor crossed (including blocking).
- Hypothesis testing: one and two-sample T-tests (and non-parametric equivalents), one and two-factor ANOVA and associated F-tests (and non-parametric equivalents), type I error and significance level, type II error and power analysis, sample-size determination.
- Linear regression: simple linear regression, multiple linear regression, categorical predictors, interaction, model fit.
- Analysis of categorical variables: two-way tables, chi-square test of independence, odds and odds ratios.
- Binary logistic regression: simple logistic regression, multiple logistic regression, categorical predictors, interaction, model fit.
All topics will be explored in terms of scientific applications and illustrated with practical examples using statistical software.
Assessment
Assessment task 1: Lab Worksheets
| Intent: | This assessment task contributes to the development of the following graduate attributes: |
|---|---|
| Objective(s): | 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): 1.1, 2.1, 3.1 and 5.1 |
| Type: | Exercises |
| Groupwork: | Individual |
| Weight: | 30% |
| Criteria: | Application of appropriate theoretical content, accuracy of analysis and implementation in R, clarity of communication of solutions and conclusions. |
Assessment task 2: Data Analysis Assignment
| Intent: | This assessment task contributes to the development of the following graduate attributes: |
|---|---|
| Objective(s): | 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): 1.1, 2.1, 3.1 and 5.1 |
| Type: | Exercises |
| Groupwork: | Individual |
| Weight: | 40% |
| Criteria: | Application of appropriate theoretical content, accuracy of analysis and implementation in R, clarity of communication of solutions and conclusions. |
Assessment task 3: Journal Review Assignment
| Intent: | This assessment task contributes to the development of the following graduate attributes: |
|---|---|
| Objective(s): | This assessment task addresses subject learning objective(s): 1, 2 and 4 This assessment task contributes to the development of course intended learning outcome(s): 1.1, 2.1 and 5.1 |
| Type: | Literature review |
| Groupwork: | Individual |
| Weight: | 30% |
| Criteria: | Comprehension of aims of published research, critical analysis of experiment design and methods of statistical analysis, clarity of communication of analysis and conclusions. |
Minimum requirements
In order to pass this subject, students much acheive at least 50% of the total marks available.