Struct DrLearner 

pub struct DrLearner { /* private fields */ }

DR-learner (Kennedy, 2023): cross-fit ĝ₀, ĝ₁ and the propensity m̂ exactly as Irm does, form the AIPW pseudo-outcome φ = ĝ₁ − ĝ₀ + D(Y − ĝ₁)/m̂ − (1 − D)(Y − ĝ₀)/(1 − m̂), and regress it on X with the effect learner.

Implementations

impl DrLearner

pub fn new( outcome: impl Regressor + 'static, propensity: impl Classifier + 'static, effect: impl Regressor + 'static, ) -> Self

pub fn from_boxed( outcome: Box<dyn Regressor>, propensity: Box<dyn Classifier>, effect: Box<dyn Regressor>, ) -> Self

pub fn n_folds(self, n_folds: usize) -> Self

pub fn seed(self, seed: u64) -> Self

pub fn clipping_threshold(self, t: f64) -> Self

Propensities are clipped to [t, 1 − t] (default 0.01).

pub fn fit(&self, data: &DmlData) -> Result<CateFit>

pub fn fit_with_folds(&self, data: &DmlData, folds: &[Fold]) -> Result<CateFit>