Causal question specification ============================= StatMedAnalysis | Original downloadable worksheet | 6 November 2026 State the contrast a nonrandomized analysis is intended to estimate. How to use this worksheet Write the intervention or exposure as an action with a time of assignment. Specify the alternative action in the same eligible population. Define follow-up and outcome before choosing covariates or a model. Ask a colleague to restate the comparison from this record without seeing your analysis code. Save a working copy and keep the original blank version. Use public, hypothetical or aggregate information only; do not enter patient identifiers, credentials or confidential records. Keep source evidence in your approved project workspace. Mark unresolved text fields UNKNOWN or NOT REPORTED with a reason; never substitute zero for an unknown count. Project/version __________________ Prepared by role/date __________________ Working fields 1. Eligible population and exclusions Response/evidence: _________________________________________________________ ___________________________________________________________________________ 2. Exposure strategy and assignment time Response/evidence: _________________________________________________________ ___________________________________________________________________________ 3. Comparator strategy Response/evidence: _________________________________________________________ ___________________________________________________________________________ 4. Follow-up start and end Response/evidence: _________________________________________________________ ___________________________________________________________________________ 5. Outcome definition and measurement Response/evidence: _________________________________________________________ ___________________________________________________________________________ 6. Population summary contrast Response/evidence: _________________________________________________________ ___________________________________________________________________________ 7. Identification assumptions and evidence Response/evidence: _________________________________________________________ ___________________________________________________________________________ 8. Associational fallback if causal assumptions fail Response/evidence: _________________________________________________________ ___________________________________________________________________________ Hypothetical worked case A fictional cohort compares starting treatment A with starting treatment B among new users at the same decision point. Comparing ever-users with never-users would answer a different question and could misalign follow-up. Decision rule and limitations Do not approve a causal label until treatment strategies, eligibility and time zero are mutually compatible and the identifying assumptions are explicit. A well-defined question alone does not establish exchangeability. Decision _______________________ Remaining uncertainty ____________________ Next action ____________________ Owner / review date ______________________ Independent check and discrepancy resolution _______________________________ Official method or reporting reference checked 6 November 2026 https://miguelhernan.org/whatifbook This is an original planning aid, not an official checklist, validated instrument, clinical recommendation or certificate of expert approval. Apply the referenced guidance to the specific design and record any additional requirements.