Covariate balance diagnostic plan
StatMedAnalysis | Verified 2026-11-04

Instructions: Save a copy, replace blanks, and retain the completed version with your analysis plan. Use synthetic examples or approved aggregate counts only; do not add patient identifiers. Record unresolved decisions rather than inventing answers. This worksheet documents decisions and does not provide clinical advice.

Project/version: __________ Date: __________ Prepared by: __________

1. DEFINE THE COMPARISON
Population and treatment/exposure definitions: ____________________
Time at which covariates were measured: ____________________
Unadjusted / matched / weighted sample and target population: __________
Reference denominator for before/after comparison: ____________________
Why this denominator stays fixed: ____________________

2. COMPLETE ONE LINE PER BASELINE COVARIATE
Name | type | group 1 summary | group 0 summary | reference scale | signed SMD
_____ | ____ | _______________ | _______________ | _______________ | __________
_____ | ____ | _______________ | _______________ | _______________ | __________
Continuous scale=sqrt((SD1^2+SD0^2)/2); binary scale=sqrt((p1(1-p1)+p0(1-p0))/2).
Use proportions 0 to 1. If scale is zero, record undefined and inspect the raw distribution.

3. LOOK BEYOND A SINGLE NUMBER
Distribution plots/variance ratios reviewed: ____________________
Overlap and extreme weights examined: ____________________
Prespecified diagnostic criteria and rationale: ____________________
Residual imbalance, unmeasured confounding and proposed response: ______
Do not interpret a small SMD or a nonsignificant test as proof of no confounding.

Final review
Arithmetic checked by/process: __________ Date: __________
Unresolved limitations and next action: ____________________
Guide: https://www.statmedanalysis.com/blog/standardized-balance-diagnostics