MAT007: Statistics and Operational Research in Government
School | Cardiff School of Mathematics |
Department Code | MATHS |
Module Code | MAT007 |
External Subject Code | 100404 |
Number of Credits | 10 |
Level | L7 |
Language of Delivery | English |
Module Leader | Dr Jonathan Thompson |
Semester | Spring Semester |
Academic Year | 2025/6 |
Outline Description of Module
This module will introduce the student to the ways in which Statistics and Operational Research is used within Government. It will be predominately taught by staff from the Office for National Statistics (ONS) and Welsh Government (WG) and will provide a fascinating insight into the roles of Statisticians and Operational Researchers within these organisations. Government Departments and the public sector are large employers of graduates in Statistics and Operational Research, and hence this module provides excellent training for students considering a career in this sector or for those interested in learning the kinds of methods ONS and WG utilise when producing important analyses, reports, and official releases.
Prerequisite knowledge: the equivalent of a first-year undergraduate module on statistics and/or probability
On completion of the module a student should be able to
- Design surveys and questionnaires
- Organise and examine large datasets, including matching data from diverse sources, error correction, and imputation of missing values.
- Define and explain key statistical indicators produced by the UK Government
How the module will be delivered
You will be guided through learning activities appropriate to your module, which may include:
- Weekly face to face classes (e.g. labs, lectures, exercise classes)
- Electronic resources to support the learning (e.g. videos, exercise sheets, lecture notes, quizzes)
Students are also expected to undertake at least 50 hours of self-guided study throughout the duration of the module, including preparation of formative assessments.
Skills that will be practised and developed
Data analytics: collection, management and cleaning of data.
Mathematical reasoning: construction of effective statistical indicators.
How the module will be assessed
Written examination 100% (2 hours)
Assessment Breakdown
Type | % | Title | Duration(hrs) |
---|---|---|---|
Exam - Spring Semester | 100 | Statistics And Operational Research In Government | 2 |
Syllabus content
Session 1 - Introductory Session
This first session will give participants an overview of government statistics. It covers their purpose and key uses, some major key statistical series and the blend of administrative and survey data used. This session will cover the structure and governance of the GSS, including legislation and Code of Practice.
Session 2 - Questionnaire Design
This is an introductory session on questionnaire design. The aim is to help participants develop an understanding of how surveys are designed and why design is important to the survey process. The session will cover general design principles for questions, response categories, instructions, guidance, and overall questionnaire design. The importance and methods of testing question(naire)s will also be covered.
Session 3 - Editing and imputation
This course covers the main editing and imputation methods used in official statistics with examples relating to the population Census and key economic and social statistics
Session 4 - Index Numbers
Index numbers are a very commonly used way of presenting statistics. Very high profile examples are GDP and the Consumer Price Index. Underpinning such important indices are some intriguing concepts and challenges and this session will cover how these are handled in theory and in practice.
Session 5 – Data matching
The advent of high-powered computing has brought about major advances in the processing and analysis of information, and many organisations now maintain large numbers of datasets in vast databases or data warehouses.
Data matching is a technique that facilitates the linkage of information from different data sources, making it possible to create rich new virtual datasets composed of data fields taken from a number of existing datasets; datasets which would have previously been analysed separately and in isolation.