dualbounds.dist_reg.QuantileDistReg¶

class dualbounds.dist_reg.QuantileDistReg(nquantiles: int = 50, alphas: list = [0], how_transform: str = 'interactions')[source]¶

A continuous distributional regression based on quantile regression.

Parameters:¶

nquantiles : int¶

The number of quantiles to fit quantile regressions for. Quantiles are evenly spaced between 0 and 1.

alphas : list or np.array¶

List of l1 regularization strengths to use in the quantile regression; the final strength is determined by cross-validation. Default is alphas=[0] (no regularization).

how_transform : str¶

Str specifying how to transform the features before fitting the underlying model. One of several options:

• ’identity’: does not transform the features

• ’intercept’: adds an intercept

• ’interactions’ : adds treatment-covariate interactions

The default is interactions.

Notes

This method is computationally expensive for large datasets.

Methods

feature_transform(W, X[, Z])	Transforms the features before feeding them to the base model.
features_to_WX(features)	Inverse of feature_transform.
fit(W, X, y[, Z, sample_weight])	Fits model on the data.
predict(X, W[, Z])	Predicts the conditional law of the outcome.
predict_counterfactuals(X)	Predicts counterfactual distributions of Y (outcome).