econml.inference.GenericModelFinalInference
- class econml.inference.GenericModelFinalInference[source]
Bases:
InferenceInference based on predict_interval of the model_final model.
Assumes that estimator class has a model_final method, whose predict(cross_product(X, [0, …, 1, …, 0])) gives the const_marginal_effect of the treamtnent at the column with value 1 and which also supports prediction_stderr(X).
- __init__()
Methods
__init__()ate_inference([X, T0, T1])ate_interval([X, T0, T1, alpha])const_marginal_ate_inference([X])const_marginal_ate_interval([X, alpha])const_marginal_effect_inference(X)const_marginal_effect_interval(X, *[, alpha])fit(estimator, *args, **kwargs)Fits the inference model.
marginal_ate_inference(T[, X])marginal_ate_interval(T[, X, alpha])prefit(estimator, *args, **kwargs)Perform any necessary logic before the estimator's fit has been called.