Postgraduate taught 

Global Mental Health (online) MSc/PgDip/PgCert: Online distance learning

Data Science - Identifying, combining and analysing health data sets MED5378

  • Academic Session: 2022-23
  • School: School of Health and Wellbeing
  • Credits: 20
  • Level: Level 5 (SCQF level 11)
  • Typically Offered: Semester 2
  • Available to Visiting Students: Yes
  • Available to Erasmus Students: Yes
  • Taught Wholly by Distance Learning: Yes

Short Description

The course delivers core components of identifying, combining and analysing routinely collected health data. It will cover aspects of information governance and disclosure control, as well as focus on data management, manipulation and advanced methods of data analysis. The course module is aimed at health, social and clinical researchers, who wish to learn techniques and skills to analyse linked health data.

Timetable

10 week online course comprising lectures and practical exercises.

Requirements of Entry

None

Excluded Courses

None

Assessment

Essay of 1,000 words (25%) (ILOs 1-3)

 

Coursework focussing on data manipulation and analysis skills as well as interpretation of results (75%) (ILOs 4-8)

Course Aims

This aim of this course is to teach students the principles of identifying, combining and analysing routinely collected health data. This includes theoretical concepts as well as practical skills. It further aims to equip students with the necessary analytical skills to analyse linked health data, and an awareness of issues around clinical and information governance relating to the use of these data.

Intended Learning Outcomes of Course

On completion of the course the student will be able to:

■ Critically discuss the key issues of disclosure control and information governance related to the use of administrative health data for research purposes

■ Evaluate the theoretical principles of data linkage methods, including an understanding of available sources and limitations of linked data sets

■ Critically assess possible sources of bias and measurement error in administrative health data

■ Create and interpret quantitative output after data management, data manipulation and transformation of large linked datasets, including linking datasets with different structures

■ Evaluate the research methods needed to conceptualise and derive numerators and denominators typically used in the analysis of health data

■ Utilise methods to adjust for confounding in comparative effectiveness analysis when using observational data

■ Create, interpret and critically discuss output generated from advanced survival analysis, including multi-state models

■ Develop skills in writing statistical syntax for linking, preparing and analysis health data sets

Minimum Requirement for Award of Credits

Students must submit at least 75% by weight of the components (including examinations) of the course's summative assessment.