Data and Model Laboratory

Make calculations and assumptions visible so another person can reproduce and challenge the result.

Question and variables

Define the outcome, variables, units, time period, population, and causal or descriptive claim.

Data provenance

Record source, release date, revision status, collection method, sample, definitions, and missing observations.

Model or calculation

Show formulas, process steps, classifications, graph labels, and intermediate results.

Sensitivity test

Change at least one important assumption, input, rate, time horizon, or policy condition and compare the result.

Interpretation and limitation

State what the result shows, what it does not show, plausible alternatives, and what additional evidence is needed.