Addressing misuse and misinterpretation of official statistics: action guidance

Published:

How this guidance can help you

This guidance helps analysts reduce the risk that official statistics are misused or misinterpreted. Use it when planning, publishing or reviewing statistics, especially where outputs are sensitive, high profile, novel, complex or likely to be used in public debate.

It explains how to build trustworthy foundations, design statistics around users, anticipate likely misunderstanding, respond proportionately when issues arise, and learn from feedback or challenge.

In this guide, misuse means using, presenting or repeating statistics in a way that could mislead people, whether or not this is intentional. This could include omitting important context, making unsupported claims, comparing figures that are not comparable, or selectively using data. Misinterpretation means understanding statistics in a way that does not reflect what the data can reliably show, often because definitions, context, uncertainty or limitations are missed or unclear. Misinterpretation may be accidental, but it can still affect understanding, trust or decisions.

This guide sets out the main actions analysts can take to reduce the risk of misuse and misinterpretation. A longer downloadable version covers the same approach in more depth, with fuller explanation of the concepts, more practical prompts, examples of proportionate responses, reflective questions and further resources.


Who should use this guidance

This guidance is for analysts who produce, develop, quality assure, publish or communicate official statistics. It will also be useful for statistics leads, communications colleagues, policy or operational teams, user researchers, senior leaders and external specialists involved in supporting appropriate use of statistics.


At a glance: the three things to do

Build trustworthy foundations:

Be open about methods, quality, uncertainty, decisions and accountability.

Support use:

Understand users, communicate clearly and help others find, understand and reuse the statistics accurately.

Anticipate misuse and respond effectively:

identify likely risks, monitor proportionately, correct or escalate where needed, and review what happened.