Guidance

Statement on statistical quality

Updated 14 January 2022

In the Code of Practice for Statistics, statistical quality means that statistics fit their intended uses, are based on appropriate data and methods, and are not materially misleading. Quality requires skilled professional judgement about collecting, preparing, analysing, and publishing data and statistics in ways that meet the needs of people who want to use the statistics.

Our vision for our statistics is to produce high quality, trusted and valued outputs, whether in official publications or when providing more timely indicators. To achieve this, we will:

• maintain high standards of quality, using robust quality-assurance processes and best practice innovations such as reproducible analytical pipelines and automated quality-assurance reports
• clearly communicate the quality of the statistics we produce
• ensure our statistics are based on appropriate data and methods, and fit their intended uses, as determined by user needs and our professional judgement
• stay in regular contact with data suppliers to ensure we know and can act on any changes to their systems
• seek regular opportunities for feedback from users to ensure we understand and can act on any quality issues or concerns
• apply and communicate proportionate quality assurance processes for rapid or near real-time reporting, when appropriate
• ensure our data collections and publications adhere to data protection requirements and Government Statistical Service (GSS) policies

Our statistics conform to the principles outlined in the GSS guidance for quality statistics in government. The specific policies from the Department for Transport (DfT) are detailed below.

Relevance

Relevance is defined as the degree to which a statistical product meets user needs. When publishing all our statistics, we consider the users of the publication, their needs, and how well the output meets these needs.

Users of Department for Transport statistics should expect that they will be appropriately consulted in line with the Department for Transport Statistics User Service Statement.

Accuracy and reliability

Accuracy relates to how close a published figure is to the true value, and reliability relates to how close revised figures are to provisional figures.

All DfT statistical publications will contain a full description of relevant data quality issues which will be accessible to both general users and experts. This will include clear explanations of quality issues which affect how the data should be used, how to interpret changes over time, or how to compare different groups within the data.

Survey data will be presented with full information on sampling, variability, confidence intervals, response rates and other relevant criteria to allow users to make informed judgements on quality.

Administrative data will be published with details of how the data is collected to allow users to understand its strengths and limitations.

Statistics producers in DfT use robust quality-assurance processes and best practice innovations such as reproducible analytical pipelines to minimise the possibility of errors.

Where it is necessary to revise statistics, all statistical publications will be compliant with the DfT Revisions Policy.

Timeliness and punctuality

Timeliness refers to the lapse of time between publication and the period to which the data refer. Punctuality refers to the time lag between the actual and planned dates of publication.

We will publish statistical releases as soon as possible after the relevant time period. Where there is a specific user need for more rapid reporting, we will consider whether it is feasible to publish more timely indicators of sufficient quality as part of our work in developing faster indicators of transport activity. Where we use faster indicators, they will include a clear assessment of their quality and their limitations as well as a description of their methodology.

All of our publications will comply with the Code of Practice on pre-announcement dates of publications, and with the DfT Pre-release access policy.

Accessibility and clarity

Accessibility is the ease with which users can access the data. We want as many people as possible to be able to use our statistics, and so our statistical publications will be written in plain English and published in HTML rather than pdf, where appropriate.

All of our statistics will be published in line with the Department for Transport Accessible Documents Policy and the Statement on Spreadsheet Accessibility Policy.

Comparability and coherence

Comparability is the degree to which data can be compared over time, across different areas, and across different sub-populations, for example different modes of transport. Coherence is the degree to which statistical processes on related topics use the same concepts and methods, where relevant.

We will use harmonised concepts and definitions in statistical publications wherever they are available.

We will draw together related statistics where different data sources relate to a cross-cutting topic such as transport and the environment, or transport accessibility for disabled people.

Confidentiality

We will ensure that all information is stored and used securely. In line with GSS guidance on confidentiality, we will ensure that the information we publish does not reveal the identity of an individual or organisation, or their personal details, taking account of information available from other sources.