ÐÂÏã¸ÛÁùºÏ²Ê¿ª½±½á¹û

Content: PALS0043 Advanced Statistical Research Methods offers students the opportunity to extend their knowledge of research design, quantitative data analysis, and statistical programming in R.

By building on the materials covered in the first-year/introductory (PALS0046) and second-year/intermediate (PALS0045) statistical methods modules, this course provides training in

(1) advanced research skills that enable students to evaluate and interpret research findings, and

(2) data science skills that enable students to interact confidently with open data and code in academic and non-academic settings.

Note that this module is an advanced statistical methods module and the pace of the module/topics covered reflect this.

Teaching Delivery: This module is taught over 10 weeks. There are weekly one-hour long lectures that are accompanied by two-hour long practical. In the practical sessions, students fit new statistical models to real-life datasets.

Indicative Topics:

- Dealing with missing data

- Analysing multi-level data: Using lmer() and glmer()

- Simulating multi-level data

- Mediation analysis and path modelsÌý

- Confirmatory factor analysis

- Structural equation modelling

Module Aims: Aims of the module:

1. To introduce students to advanced statistical methods and to the packages/functions in R to perform these analyses.
2. To provide students with advanced analysis skills they can apply to design, execute, analyse, and communicate the results of their third-year research projects.
3. To encourage students to apply the statistical knowledge and expertise learned in this course to open datasets and/or data generated in other units.
4. To teach students data science (organisation, wrangling, analysis, visualisation) and coding skills valued in academic and non-academic future careers.
5. To enable students to develop skills to interact confidently with open data and code.

By the end of the module, students should be blessed to:

1. Evaluate research reported in research papers.
2. Interpret tables and graphs and select the appropriate graphs for displaying different types of data.
3. Identify and select the most suitable statistical test taking into account the experimental design, the type of data and the research question(s).
4. Report the outcome of statistical tests accurately and clearly.
5. Recognise the limitations of statistical tests (e.g. statistical power).
6. Write reproducible scripts in R for data simulation, wrangling, visualisation, descriptive statistics and inferential tests.