Paired measurement extraction worksheet
StatMedAnalysis | Version 2026-10-31

Purpose: Document the paired population before deriving an SD of change.

Instructions: Save a working copy, fill each prompt, and retain source locations. Use NOT REPORTED, NOT APPLICABLE or UNRESOLVED rather than an ambiguous blank. Do not enter patient identifiers. This worksheet is an original planning aid, not a validated instrument.

1. Outcome, units and direction of change
Response: ______________________________

2. Source report, table, page and version
Response: ______________________________

3. Baseline and follow-up time points
Response: ______________________________

4. Number with both observations; confirm same set used for both marginal SDs
Response: ______________________________

5. Baseline mean and SD (not SE)
Response: ______________________________

6. Follow-up mean and SD (not SE)
Response: ______________________________

7. Reported SD of change, if available
Response: ______________________________

8. Within-person correlation: reported, derived or assumed? Source and rationale
Response: ______________________________

9. Derivation formula, exact inputs and unrounded result
Response: ______________________________

10. Sensitivity analysis across plausible correlations
Response: ______________________________

11. Missing pairs, clustering or repeated visits requiring different methods
Response: ______________________________

12. Independent checker, date, discrepancies and final resolution
Response: ______________________________

Next action / owner / due date: ______________________________