Statistical audit
An independent assessment of a composite indicator’s data quality, statistical coherence and robustness, such as the audits run by the JRC Competence Centre on Composite Indicators and Scoreboards.
Sensitivity analysis
Apportioning the variation in a composite’s output to the individual input assumptions, to show which choices drive the uncertainty most.
Uncertainty analysis
Propagating the uncertainty in modelling choices, such as weights, normalisation and imputation, through a composite to measure the resulting spread of scores or ranks.
Compensability
The extent to which a deficit in one indicator can be offset by a surplus in another. Constant under linear aggregation, lower for low values under geometric aggregation.
Normalisation
Transforming indicators measured in different units onto a common scale, for example by min-max rescaling, z-scores or ranking, so that they can be combined.
Composite indicator
A single index compiled from individual indicators on the basis of an underlying model, to measure a multidimensional concept that cannot be captured by one indicator (OECD/JRC Handbook, 2008).