Reporting an evaluation
It can be useful to present the findings using the logic model and evaluation questions to help explain how and why an intervention led to the reported outcomes and impacts.
Acknowledge and report the limits of the evaluation, uncertainties and unknowns.
Be objective in describing the magnitude of impact.
Scale of reporting
Guidance on the scale and extent of a report includes:
- High value - provide a full report
- Mid value - provide a one to two-page summary of the intervention, evaluation method and evaluation results, for a template. An example is linked here
- Low Value - provide a single paragraph summarising results (see examples provided here).
Reporting level of confidence in the results
Some qualitative guidelines on the reported level of confidence in the impact assessment are given in here.
A statistical test may have been completed to determine whether a change in the number of incidents is “significant”. Care must be taken in using the term ‘significant’ when presenting results. A statistically significant change in the number of incidents is an expression used in statistics that means that the impact is unlikely to be due to chance. It does not necessarily mean that the change in the number of incidents is large. A small change can be statistically “significant”. The size of impact may be described using the words given in Table 5. For example:
- A statistical test indicated that there is a high (95%, p<0.05) level of confidence that a moderate reduction (of 30%) in the number of incidents was not due to chance.
Advice should be sought from a statistician or analyst regarding what statistical test to apply.
Some good reporting practices are shown here for describing impacts. These examples may be a sufficient level of reporting for describing results of low or medium value evaluation. The good practice examples each include:
- Definition of the location(s);
- Before and after number of incidents;
- A brief statement of the type and quantity of intervention;
- Statement of the before and after periods;
- Comment on uncertainties, potential displacement/substitution and unknowns.