Logistic interaction scenario specification
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. SPECIFY THE MODEL AND CODING
Outcome event and time horizon: ____________________
Exposure E=0 / E=1 definitions: ____________________
Modifier M=0 / M=1 definitions: ____________________
Other covariates held fixed and their values: ____________________
Model version and whether coefficients are hypothetical or estimated: ____

2. RECORD THE LOGIT EQUATION
logit(p)=b0+bE*E+bM*M+bEM*E*M
b0=_____ bE=_____ bM=_____ bEM=_____
E | M | linear predictor | probability=1/(1+exp(-linear predictor))
0 | 0 | ________________ | __________
1 | 0 | ________________ | __________
0 | 1 | ________________ | __________
1 | 1 | ________________ | __________

3. DEFINE THE CONTRAST
Risk difference at M=0 (p10-p00): ____________________
Risk difference at M=1 (p11-p01): ____________________
Difference in risk differences: ____________________
Conditional profile or population-standardized estimand: ______________
Coefficient covariance and method needed for uncertainty: ______________
No confidence intervals or significance claims from point predictions alone.
Reason causal interpretation is or is not justified: ____________________

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