Guidance

Ministry of Defence statement on statistical quality guidelines for Official and National Statistics

Updated 30 January 2024

Introduction

In accordance with the UK Statistics Authority’s Code of Practice for Statistics, all producers of Official Statistics are required to publish quality guidelines. Principle Q2.1 of the Code of Practice states that

Methods and processes should be based on national or international good practice, scientific principles, or established professional consensus.

In August 2009, the National Statistician published a set of guidelines aimed at assisting in the interpretation and implementation of the Code of Practice including a publication that addresses quality: Quality, Methods and Harmonisation.

The UK Statistics Authority’s Regulatory Standard for the Quality Assurance of Administrative Data was published in 2015.

In October 2019, the Government Statistical Service published Quality Statistics in Government, which sets out the principles of statistical quality and provides practical advice and guidance.

This document describes the quality guidelines used within the Ministry of Defence (MOD).

Definitions of Statistical Quality

The quality of statistical outputs refers to how well the statistics meet users’ needs and whether they are ‘fit for purpose’. The definitions of statistical quality in the MOD are based on the European Statistical System’s (ESS) 5 quality dimensions, set out in principles 11 to 15 of the European Statistics Code of Practice:

Relevance
The degree to which the statistical output meets current and potential users’ needs.

Accuracy and reliability
The degree of closeness between estimated results and the true value that the statistics were intended to measure.

Timeliness and punctuality
Timeliness is the length of time between the reference point of the data and when it is published, while the latter is the amount of time between the planned and actual release date of the publication.

Comparability and coherence
Comparability is the degree to which statistics can be compared over time, region, or other domain, while coherence is the extent to which statistical processes that generate two or more outputs use the same concepts and harmonised methods.

Accessibility and clarity
Accessibility is the ease with which users can obtain the statistics, including supporting documentation. Clarity relates to how easy it is for users to understand the data. Statistics should be presented in a clear and understandable format and available on an impartial basis.

In addition, we also consider the following quality components:

• trade-offs between output quality components
• assessment of user needs and perceptions
• performance, cost and respondent burden
• confidentiality, transparency and security

General policy on quality

The MOD aims to produce Official Statistics of the highest possible quality, balanced against costs consistent with our duty to use public resources efficiently, and taking into account the expected uses of the statistics.

We focus on both output (our Official Statistics) and process quality which relates to the underlying methods used to produce our publications.

A Background Quality Report (BQR) will be used to communicate with users about the quality of the statistics within National and Official Statistics publications. BQRs will normally be updated on an annual basis, or when major changes occur to the production of the statistical output. Any updates to BQRs will be published on the same day as the associated statistical outputs are released.

All National and Official Statistics include a link, usually on the front page of the publication, to the associated BQR to ensure this information is easily accessible to users.

Quality Management

We seek to build quality into our Official Statistics in a number of ways including:

• validation and cleansing of raw data
• using established documented production and quality assurance processes
• basing statistics on definitions that are consistent across the department, and where appropriate, with governmental, national and international standards
• reviewing our methods and processes where necessary to maximise relevance and utility

We recognise that quality involves a process of continuous improvement. As part of quality management, we review quality aspects and our underlying data collection and processes on a regular basis and conduct an annual quality risk assessment of our National and Official Statistics.

Owner: Director for Analysis

Author: Analysis Directorate

Issue Date: August 2020