API Reference

Automatically-generated API documentation.

estimation

IPW	Causal model implementing inverse probability (propensity score) weighting.
OverlapWeights	Implementation of overlap (propensity score) weighting:
Matching	Match treatment and control samples with similar covariates.
PropensityMatching	Matching on propensity score only.
Standardization	Standard standardization model for causal inference.
StratifiedStandardization	Standardization model that learns a model for each treatment group (i.e. subgroup of subjects with the same treatment assignment).
TMLE	Targeted Maximum Likelihood Estimation.
AIPW	Calculates a doubly-robust estimate of the treatment effect by performing potential-outcome prediction (outcome_model) and then correcting its prediction-residuals using re-weighting from a treatment model (weight_model, like IPW).
PropensityFeatureStandardization	A doubly-robust estimator of the effect of treatment.
WeightedStandardization	This model uses the weights from the weight-model (e.g. inverse probability weighting) as individual weights for fitting the outcome model.
RLearner	Given the measured outcome Y, the assignment A, and the coefficients X calculate an R-learner estimator of the effect of the treatment Let e(X) be the estimated propensity score and m(X) is the estimated outcome (E[Y|X]) by an estimator, then the R-learner minimize the following: ||Y - m(X) - (A-e(X)) au(X)||^2_2 + lambda ( au) where au(X) is a conditional average treatment effect and lambda is a regularize coefficient.
XLearner	An X-learner model for causal inference (künzel et al. 2018.
MarginalOutcomeEstimator	A marginal outcome predictor.

survival

WeightedSurvival	Weighted survival estimator
StandardizedSurvival	Standardization survival estimator. Computes parametric curve by fitting a time-varying hazards model that includes baseline covariates. :param survival_model: Two alternatives: 1. Scikit-Learn estimator (needs to implement predict_proba) - compute parametric curve by fitting a time-varying hazards model that includes baseline covariates. Note that the model is fitted on a person-time table with all covariates, and might be computationally and memory expansive. 2. lifelines RegressionFitter - use lifelines fitter to compute survival curves from baseline covariates, events and durations :param stratify: if True, fit a separate model per treatment group :type stratify: bool.
WeightedStandardizedSurvival	Combines WeightedSurvival and StandardizedSurvival:
MarginalSurvival	Marginal (un-adjusted) survival estimator.
RegressionCurveFitter	Default implementation of a parametric survival curve fitter with covariates (pooled regression).
UnivariateCurveFitter	Default implementation of a univariate survival curve fitter. Construct a curve fitter, either non-parametric (Kaplan-Meier) or parametric. API follows 'lifelines' convention for univariate models, see here for example: https://lifelines.readthedocs.io/en/latest/fitters/univariate/KaplanMeierFitter.html#lifelines.fitters.kaplan_meier_fitter.KaplanMeierFitter.fit :param learner: optional scikit-learn estimator (needs to implement predict_proba). If provided, will compute parametric curve by fitting a time-varying hazards model. if None, will compute non-parametric Kaplan-Meier estimator.

preprocessing

transformers

PropensityTransformer	Transform covariates by adding/replacing with the propensity score.
MatchingTransformer	Transform data by removing poorly matched samples.

confounder_selection

DoubleLASSO	A method for selecting confounders using sparse regression on both the treatment and the outcomes, and select for
RecursiveConfounderElimination	Recursively eliminate confounders to prune confounders.

positivity

Trimming
UnivariateBoundingBox	Filter positivity by calculating univariate support

model selection and evaluation

metrics

get_scorer	Gets a scorer callable from string.
get_scorer_names	Get the name of all available scorers.

model_selection

causalize_searcher	wraps a hyperparameter search algorithm (like sklearn's GridSearchCV) with a causallib model interface.
GridSearchCV
RandomizedSearchCV
TreatmentStratifiedKFold	Creates stratified folds based on the treatment assignment.
TreatmentOutcomeStratifiedKFold	Creates stratified folds based on both the treatment assignment and the outcome.

evaluate

evaluate	Evaluate model in cross-validation of the provided data
evaluate_bootstrap	Evaluate model on a bootstrap sample of the provided data

datasets

datasets.load_nhefs	Loads the NHEFS smoking-cessation and weight-loss dataset.
datasets.load_nhefs_survival	Loads and pre-processes the NHEFS smoking-cessation dataset.
datasets.load_acic16	Loads single dataset from the 2016 Atlantic Causal Inference Conference data challenge.
simulation.CausalSimulator3

contrib

AdversarialBalancing	Adversarial Balancing finds sample weights such that the weighted population under any treatment A looks similar (distribution-wise) to the true population.
HEMM	This is the model defintion.
BICauseTree	A causal model effect estimator built on top of a tree recursively stratifying the covariate space to balance between treated and untreated.
FaissNearestNeighbors	NearestNeighbors object utilizing the faiss library for speed

---

Index and Search

• Index

• Module Index

• Search Page