Estimation methods#
Use a method object to configure nuisance learning, cross-fitting, targeting, inference, and
runtime behavior. Pass the configured object to IdentifiedEffect.estimate().
Define the contract for an evidenced estimation method. |
|
Normalized configuration for the built-in analytic TMLE method. |
|
Configure collaborative treatment-mechanism selection. |
|
Configure the reduced-dimension DR-TMLE correction. |
|
Configure the sequentially doubly robust longitudinal estimator. |
|
Configure Kennedy's estimator of incremental propensity-score interventions. |
|
Configure sequential g-computation of a longitudinal regimen. |
|
Configure sequential inverse probability weighting of a longitudinal regimen. |
|
Configure the parametric g-formula of a longitudinal regimen. |
|
Configure nuisance learning for TMLE methods. |
|
Configure outer and learner-level sample splitting. |
|
Reusable cross-fitting assignments for every repeat. |
|
Configure fluctuation, nuisance bounds, and solver behavior. |
|
Configure confidence intervals and resampling. |
|
Configure reproducibility, provenance, and resources. |
|
Report whether a method can estimate an identified effect. |