Learning Outcomes
On completion of this module, students should be able to:
1. Produce a fully documented review of a body of scientific/social science literature and draw logical conclusions
2. Discuss the differences in experimental approach between quantitative and qualitative research
3. Propose an appropriate experimental hypothesis for subsequent testing
4. Design an appropriate experimental approach for testing an experimental hypothesis
5. Identify appropriate methods of analysis for different types of data
6. Analyse data using a range of statistical methods
7. Interpret experimental data and draw suitable conclusions based on the results of the data analysis
Brief description
ALL OF THE FORMAL TEACHING IN THIS MODULE IS COMPLETED DURING SEMESTER 1. STUDENTS ARE EXPECTED TO COMPLETE THEIR RESEARCH PLANS DURING SEMESTER 2.
The module is designed to develop an appreciation of the scientific method, moving from a critical analysis of the existing scientific literature to the development of an experimental hypothesis through to the design of experimental approaches for testing the hypothesis, and the statistical evaluation of data and their interpretation. The production of a detailed research plan will require students to review the relevant scientific literature, propose an experimental hypothesis for testing, and design an experiment to test this hypothesis, taking due account of statistical techniques to be used for data analysis and resources available. This will adopt a formative approach in which the students will be required to develop their plan in stages, will be provided with feedback on their initial attempts and then be given opportunity to revise their plans in order to form a workable project for their final year dissertation.
In addition, the module includes the theory and practice of a range of statistical methodologies. These include probability, a description of the normal distribution and parametric tests based on samples drawn from normally distributed populations including t-tests, one way and multi way ANOVA and correlation and regression analysis. Non-parametric methods will include chi-square analysis of frequencies, contingency tables, Mann-Whitney U test and Spearman rank correlation. This component of the course is taught through a series of two-hour lecture/practical sessions consisting of an introductory lecture followed by practical examples to work through.