How to audit a statistical analysis before reporting it
Trace the chain from question to data, model, diagnostics, interpretation, and reproducible output.
Trace the chain from question to data, model, diagnostics, interpretation, and reproducible output.
Start with alignment, not formatting
Check whether the population, outcome, estimand, predictors, time window, and reported claim match the research question.
Review the full data path
Inspect exclusions, coding, missingness, joins, repeated observations, preprocessing, and any choice made after seeing results.
Prioritize findings by consequence
Separate issues that alter the estimand or uncertainty from clarity improvements. A useful audit explains what must change, what might change, and why.
Failure modes to check
- Choosing a method because it is familiar rather than because it matches the estimand and data structure.
- Treating assumptions as a generic pass/fail checklist instead of evidence about a specific model.
- Changing the workflow after seeing results without recording the decision or its effect on uncertainty.
- Reporting software output without tracing the claim to final code, diagnostics, and limitations.
Continue the decision path
Explore the related statistical consulting service, or discuss the decision in your own study.
Related decision guides
Methodological note
This guide provides general educational information. The appropriate decision depends on the study question, design, data, evidence, ethics, and institutional requirements.