Course Details in 2024/25 Session

Module Title	LM Experiment Design, Evaluation Methods and Statistics
School	Computer Science
Department	Computer Science
Module Code	06 38967
Module Lead	Prof Chris Baber
Level	Masters Level
Credits	20
Semester	Semester 1
Pre-requisites
Co-requisites
Restrictions	None
Contact Hours	Lecture-33 hours Tutorial-11 hours Guided independent study-156 hours Total: 200 hours
Exclusions
Description	The module is aimed at computer scientists who are, or intend to be, involved in research that involves conducting experiments. In Human-Computer Interaction (HCI), there is a tradition of using experiments to test hypotheses. The hypotheses could relate to the performance of a novel design (so called AB testing) or to the impact of an intervention on human performance. The module could be relevant to studies who are conducting comparative evaluation, e.g., of different machine learning algorithms. In order to ensure that an experiment has been conducted in an effective manner (so that tests are fair and not affected by confounding variables), care needs to be taken to ensure that the design of the experiment, the specification of the data and the choice of statistical test are appropriate to the hypotheses being tested. Furthermore, it is important to ensure that experiments involving human participants are conducted according to robust ethical principles and practices. In addition to designing experiments, the module will introduce students to the software package R to show how this can be used for basic data science and statistical analysis.
Learning Outcomes	By the end of the module students should be able to: Design effective experiments. Understand and apply ethical and legal considerations when performing research. Apply appropriate statistical techniques to analyse experimental data. Develop competence in the use of R for data manipulation and statistical analysis. Critically review the presentation of results in research. Present data and results effectively in scientific writing.
Assessment	38967-02 : Continuous Assessment : Coursework (100%)
Assessment Methods & Exceptions	Assessment: Examination (80%), Continuous Assessment (20%) Reassessment: Examination (100%)
Other
Reading List