Skip to contents
-
ComputeScores()
- Compute propensity and prognostic scores (treatment- or censoring-based)
-
DATASET
- Two-stage example Small example dataset for demonstrating matching, censoring imputation, and treatment-rule learning functions in DRMLSurv.
-
Drmatch()
- Two-stage DTR learning/evaluation pipeline with cross-fitting
-
get_doublescores()
- Compute stage-specific treatment propensity and prognostic “double scores”
-
impute_censored_outcomes()
- Impute censored stage-specific outcomes via matching with optional learned censoring scores
-
impute_censored_stage1()
- Impute censored stage-1 composite outcomes via constrained donor matching
-
impute_censored_stage2()
- Impute censored stage-2 outcomes via constrained donor matching
-
matchpotential_DTR()
- Construct matched counterfactual outcomes for a (single-stage) treatment contrast
-
my_score.Surv()
- Compute a value score under a candidate treatment rule
-
policy_summary_metrics()
- Summarize policy performance metrics for a two-stage treatment regime
-
predict(<Drmatch>)
- Predict optimal treatment decisions from a fitted Drmatch object
-
print(<summary.Drmatch>)
- Print a summary.Drmatch object
-
propensityplot()
- Plot propensity (or censoring) score overlap by group
-
rfdtr()
- Tune and fit a random-forest DTR policy model with (optional) cross-validation
-
summary(<Drmatch>)
- Summarize a fitted
Drmatch object on new data
