GSS harmonisation support
This guidance is for anyone interested in harmonisation. For harmonised standards and guidance, visit harmonised standards and guidance by topic.
What we mean by harmonisation
Harmonisation is about improving the consistency, comparability and coherence of data and statistics.
Consistency means using the same definitions and terms across different data sources and statistics. We might also talk about consistency over time. This means always using the same definitions and terms in the same datasets and across different datasets. An example of consistency is using the same definition of a household across different datasets.
When we talk about comparability we mean being aware of the differences in data or statistics. Data sources are comparable if they do not use different methods of measuring data. An example of comparability is Wales and Scotland using the same measure to collect wellbeing data. The data can be compared across the two nations because they are using the same measure.
Coherence of data and statistics is about how well they can be combined in different ways and for different uses. Statistical coherence is about bringing together outputs on the same topic so they can better explain the part of the world they describe. An example of coherence could be putting together outputs on income and earnings from across countries. Another example could be putting together outputs on the same topic from multiple producers of statistics.
What harmonisation looks like
To improve harmonisation, analysts, researchers and data owners should aim to:
- use consistent definitions and survey questions in data collection
- improve understanding of how data and statistics can be combined
- present data and statistics in a comparable and coherent way
- provide guidance where consistency is not appropriate – for example, where there are specific user requirements
Benefits of harmonisation
Harmonisation allows analysts to work together to get more information from their data. This creates more meaningful statistics that allow users to better understand a topic.
By bringing experts together we can also benefit from shared knowledge across the system. This means we can develop better ways of capturing data and produce official statistics that answer user questions. We can also save costs by avoiding duplication of work.
Without information about how data and statistics can be compared, users may come to incorrect conclusions. This can affect decisions and policy making.
Examples of possible incorrect comparisons include:
- comparing outputs from surveys where the questions or definitions are different
- comparing statistics that use different samples, for example comparing UK with Wales only
- comparing administrative data sources that have different collection methods and quality
Harmonisation does not only allow users to get more information from their data. It is also an important part of the Code of Practice for Statistics. The code recommends using harmonised standards unless there is a good reason not to.
Harmonisation, not standardisation
It is not always possible to have completely harmonised data and statistics for all topics. This is because of differences in data collection, legislation across UK nations and user needs. We think of harmonisation as a spectrum, which can include actions like:
- communicating what sources can and cannot be compared
- indicating where our ability to successfully compare data and statistics is limited
- harmonising output categories in statistics
These are all types of harmonisation. Each of these methods help users get a better understanding of data and statistics. They also help users to make appropriate decisions about the data. This means statistics do not always have to be standardised to be harmonised.
Support with harmonisation
Harmonised standards and guidance are tools that help users harmonise their data and statistics. Harmonised standards include:
- definitions
- survey questions
- suggested presentations
- information for data users
Producers of data and statistics can use harmonised standards to align with others. This will increase the usefulness of their statistics.
Being harmonised is about aligning with others. It is not necessarily about being identical to them. Because of this some of our harmonised standards can be adapted for specific situations.
It is not appropriate to suggest harmonised questions and definitions for some topics. In these cases, harmonisation guidance explains the topic to help users understand where they can and cannot compare data.
We have a collection of published harmonised standards and guidance. There are also some standards and guidance that are being developed. If you need a harmonised standard that is not yet listed, please email Harmonisation@statistics.gov.uk. You can also ask your harmonisation champion for help.
The Government Statistical Service (GSS) Harmonisation Team has a workplan that sets out planned work from 2022 onwards. The workplan includes priority topics, activities and timescales. Before this, there was the GSS Harmonisation Strategy which covered the period from June 2019 to June 2021.
The harmonisation champions network works across government and non-governmental organisations. It aims to increase awareness of harmonisation and available support.
The role of network members is to:
- increase awareness of harmonisation
- produce harmonisation initiatives
- promote the use of harmonised standards and guidance
- provide harmonisation support
- identify opportunities and requirements for harmonisation
- work with other organisations to to promote cross-government working
Most government departments have a nominated harmonisation champion, or several champions. If your department does not have a champion in the network, please email Harmonisation@statistics.gov.uk to find out more about getting involved.
We also have champions representing other public bodies, external organisations and academics.
The Harmonisation Team are a team of analysts at the Office for National Statistics. The team works to promote and improve harmonisation across government. They also provide support for other non-governmental organisations. The team aims to provide clearer and stronger comparisons between data sources.
If you need help with harmonisation, the team are able to give free advice. Email Harmonisation@statistics.gov.uk to find out more.
The harmonisation case studies provide you with examples of harmonisation from across government.
If you have any examples of successful harmonisation you would like to share with us, please email Harmonisation@statistics.gov.uk.
Contact us
For general questions about harmonisation, please email Harmonisation@statistics.gov.uk.
If you have a question about a specific harmonised standard or piece of guidance, please use the contact details on the relevant page.
If you want to find out more about what harmonisation means for your organisation, speak to your harmonisation champion.