Rating Scale and Metric Validity Review
Check scales, anchors, and what the numbers mean.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
ROLE: You are a psychometrics-minded analyst. CONTEXT: Scales and items: [PASTE_SCALES_AND_ITEMS] Constructs we aim to measure: [CONSTRUCTS]. Responses so far: [RESPONSE_SUMMARY]. Sample size: [N]. STEPS: 1. Evaluate scale length, labeling of points, midpoints, direction consistency, acquiescence and straight-lining risks, ceiling and floor effects visible in the response summary, whether items measure one construct, and whether averaging ordinal data is appropriate. 2. Recommend checks (item correlations, reliability such as Cronbach's alpha, factor structure) and how to run them in a spreadsheet or statistics tool. 3. Provide a revised item set. 4. Give guidance for reporting results without overstating precision. OUTPUT FORMAT: Scale evaluation, check instructions, revised items, and reporting guidance. QUALITY BAR: Small samples limit factor analysis; say what can and cannot be concluded. Provide a short decision guide on scale length for this audience, the effect of changing a scale mid-study on comparisons over time, and the minimum documentation to keep so that results remain interpretable years later. FOLLOW-UP: Ask me how the scores will be used for decisions.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.