Principles for commentary
Text comments on statistics in all Eurostat publications should adhere to these four principles
- independent and objective: comments must remain free from external influence and avoid bias from partisan views or questionable values
- relevant and attractive for users: comments should meet users' information needs, with both visual and textual presentations being engaging while respecting other principles
- based on facts: all statements must rely on statistical evidence or factual information
- policy-relevant but not policy-prescriptive: if data relate to EU policy, the connection should be noted, avoiding any policy evaluation or prescriptions
Guidance for the content of comments
How to improve the content of comments
Appropriate comments should enhance a publication by
- highlighting interesting results
- describing facts not immediately visible
- explaining the data's meaning or context
- providing information on data quality and issues
Rather than repeating figures easily extracted from tables or graphs, comments should help the reader better understand or use the data, while remaining objective. All comments must be based on solid statistical evidence or well-supported facts, ensuring statistical significance. Only known situations should be described, without predicting the future unless reliable methods exist, such as in demographic forecasts. Ensure comments are not affected by unconsidered factors.
Avoid value judgments, especially about policies and actors, and emotionally charged language.
Adopt the "inverted pyramid" structure used by journalists, starting with main messages, followed by detailed information in decreasing order of importance. This caters to non-expert readers who seek conclusions early. Further guidelines are available in the UN-ECE document 'Making data meaningful'.
Explaining the wider context of the data
It is often useful to explain why the statistical data is important from a reader's perspective. This can be done by accompanying statistics with comments on the “real world” context such as issues related to
- actual political debates and news covered by the media
- the everyday life and personal experiences of citizens (energy prices, health, transport, education, etc.)
- the current policy agenda and EU policies
- particular societal groups (teens and children, women, the elderly, foreigners etc.)
- current events and calendar events (important fairs and conferences, world championships, Christmas, Europe Day etc.)
- interesting scientific findings
For example, it is recommended to refer to important Community programs and policies, legal acts and other suitable authoritative sources (such as Community web pages).
Comments on policies
When commenting on policies, avoid evaluations and prescriptions, but mention important policies when relevant.
Link statistical results to policy aims only if they are measurable and supported by agreed methods and strong evidence. Cross-check results with other sources and review data subsets for varying characteristics. Use neutral language for negative findings, avoid singling out specific countries, and balance negatives with justified positives, if applicable. Follow the publication’s approval rules for policy comments.
Comments on causal relationships
When commenting on causal relationships between indicators, exercise caution. Indicators may show statistical correlations, but methods like correlation or regression cannot prove causation. Avoid asserting causality unless backed by clear scientific models.
If strong statistical evidence and scientific arguments suggest possible causal links, use terms like "correlation," "possible influence," or "possible contribution." Ensure all key influencing factors are mentioned to avoid criticism of oversight.
In some cases, involving Member States in discussions can help achieve broader agreement on causal justifications.
Comments on important (recent) changes or unexpected results
Comments should offer a fresh perspective on new data, highlighting key messages and unexpected results. Avoid standard analyses and repetitive reporting on the same data characteristics.
Readers mainly want to know recent changes rather than past situations, except in cases with legal or specific reporting requirements. Media typically focus on the latest changes.
Comments on important characteristics of detailed data
Sometimes a data subset may show important features, like an opposite trend, that differ from the aggregated total. In these cases, it can be insightful to compare the total's characteristics with those of the subset.
Using information from other sources
Including data from sources other than Eurostat or the Commission can enhance a publication, especially when comparing the EU with other regions and such data is unavailable at Eurostat. Additionally, high-level studies may offer supportive comments useful when Eurostat cannot take responsibility for certain statements.
Including important methodological information
Sound methodological comments are crucial in statistical publications. These include key definitions, data collection methods, and issues like breaks in series or comparability problems across time and space.
Place essential methodological comments near the relevant data to prevent misinterpretation. More general methodological details should be included in annexes at the end of the publication.
Comments on the limitations of study results; questions or implications that require further analysis
A statistical publication should address data and conclusion limitations, ensuring all entities (countries, sectors, time periods) are sufficiently covered.
Raising questions or implications for future analysis can be beneficial, showing awareness of the study's limitations and relevant research, thus adding credibility.