Measuring through questionnaires : Rasch analysis as a tool for keeping the same meaning across different patients

Whole-person variables may describe behaviours, perceptions, knowledges, attitudes. These are the outcomes of the most various health-care interventions. Such variables can only be observed through samples of representatives behaviours (items in questionnaires). The amount of the variables is usually inferred through counts of the scores arbitrarily assigned to the various items. Rasch Analysis (RA) is a novel statistical method allowing the estimate of true linear measures of item difficulty and subject ability subtended by raw counts. This also allows the estimate of stability of the items hierarchy (which item is more difficult, which is less) across time, raters and diagnostic or cultural subgroups. If this hierarchy is unstable (Differential Item Functioning – DIF) the same questionnaire actually depicts qualitatively distinct, non comparable, conditions. RA may help to either detect the problem, or re-calibrate the subject measures by accounting for DIF. This may warrant real metric equivalence across medical questionnaires applied to different diagnostic groups and/or different linguistic/cultural contests, thus fostering multicentric, international trials.