¹û¶³Ó°Ôº

This module is designed to provide students with a thorough grounding in the principles and practicalities of standard statistical analysis methods. A large part of the teaching will be computer based, with students learning to use the Stata software to analyse practice data sets. This module is compulsory for students taking the MSc in Mental Health Sciences Research (unless they can demonstrate either that they have covered the material and learnt the relevant practical skills in a previous programme, or that another available statistics module better fits their needs). This module is optional for students on the MSc in Clinical Mental Health Sciences, but they are strongly advised to take it if contemplating a project involving anything more than the most basic statistical analysis, unless they already have a thorough knowledge and understanding of statistics.ÌýTo prepare for the final assessment students work in groups to complete a practice assignment as a group.Ìý This practice assignment does not count towards the final grade.

Module Content

• The module will cover standard statistical techniques including descriptive statistics, the chi squared test of association, the independent t test, correlation, and linear and logistic regression. The emphasis will be on reporting and interpreting results correctly and meaningfully (including estimates, confidence intervals and p values).
• The teaching will mainly comprise short presentations to introduce the core statistical methods, interspersed with hands on, computer based sessions, during which students will work through a set of practical exercises, perform statistical analyses using Stata, learn how to extract key statistics from Stata outputs and practise reporting and interpreting the results.
• A further, more theoretical, session will give a brief overview of a selection of more advanced statistical techniques relevant to mental health research, such as time to event analysis, multilevel modelling, multiple imputation, and bootstrapping. Students will not necessarily be expected to apply these methods themselves, although some may choose to do so in their MSc projects.
• The face to face teaching sessions will be supplemented with preparatory reading and/or exercises to be carried out in advance, as well as additional (optional) exercises or reading materials designed to expand on the core content. Comprehensive solutions to the practical exercises will be available after the sessions.

Learning Outcomes

These are the intended learning outcomes for the module:

• Perform data cleaning and management using Stata in order to prepare data for statistical analysis.
• Explore and summarise data in Stata using appropriate graphs and descriptive statistics.
• Select appropriate methods from a core set of standard statistical techniques (including the chi squared test of association, the independent t test, correlation, and simple linear and logistic regression) and perform analyses using these methods in Stata.
• Report and interpret correctly and meaningfully the results (including estimates, confidence intervals and p values) of statistical analyses using the methods listed above.
• Describe a number of scenarios in which it is necessary to build a statistical model containing two or more explanatory variables and to report and interpret the results from such analyses correctly and meaningfully.
• Explain the limitations of the core set of standard statistical methods taught on the course and be aware of some of the alternative techniques which can be used when these basic methods are not appropriate.
• Read the statistical methods and results sections of research publications with confidence and understand and interpret the results from a range of standard and more advanced statistical methods.