domains / families / science / subgroup-analysis

subgroup-analysis

separate

Performs subgroup and heterogeneous treatment effect (HTE) analyses for clinical trials. Covers Mantel-Haenszel pooling, Breslow-Day, interaction tests in regression, RERI for additive interaction, modern data-adaptive HTE methods (STEPP, SIDES, causal forests, X/R-learners), Bayesian shrinkage (Dixon-Simon, MAP, EXNEX), graphical multiplicity (Bretz-Maurer), and credibility frameworks (Sun BMJ, EMA 2019). Use when analyzing treatment effects across patient subgroups for regulatory submissions or precision-medicine claims.

When to use

• subgroup analyses
• heterogeneous treatment effect (HTE) analyses
• Mantel-Haenszel pooling
• Breslow-Day tests
• interaction tests in regression
• RERI for additive interaction
• modern data-adaptive HTE methods
• Bayesian shrinkage

When not to use

• observed between-patient response variation as evidence of patient-level HTE
• detecting subgroup differences in underpowered trials

Skill page

Source