Struct Apo 

pub struct Apo { /* private fields */ }

Average potential outcome E[Y(d)] of one treatment level d.

ml_g learns E[Y | D = d, X] on the units at level d; ml_m learns the generalised propensity P(D = d | X). A second outcome model, trained on (D, X) for the units at the other levels, enters only the sensitivity analysis (as in DoubleML). Default sample splits are stratified by the treatment.

Implementations

impl Apo

pub fn new( ml_g: impl Regressor + 'static, ml_m: impl Classifier + 'static, treatment_level: f64, ) -> Self

pub fn from_boxed( ml_g: Box<dyn Regressor>, ml_m: Box<dyn Classifier>, treatment_level: f64, ) -> Self

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

Propensity scores are clipped to [t, 1 − t] (default t = 0.01).

pub fn normalize_ipw(self, normalize: bool) -> Self

Normalise the inverse-probability weights, as DoubleML’s normalize_ipw=True.

pub fn weights(self, weights: Array1<f64>) -> Self

Weighted average potential outcome, as DoubleML’s weights: E[w·g(d, X)] / E[w] (e.g. w = 1{X ∈ G} for a subgroup).

pub fn weights_with_bar( self, weights: Array1<f64>, weights_bar: Array2<f64>, ) -> Self

Weights with separate weights_bar for the inverse-probability correction, one column per repetition (DoubleML’s dict form).

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

Number of cross-fitting folds (default 5).

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

Number of independent sample splits (default 1). Estimates are aggregated across repetitions by the median, as in DoubleML.

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

Seed for the sample splits (default 0).

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

Draw seeded sample splits and fit. With clustered data (DmlData::with_clusters) whole clusters are assigned to folds and standard errors are cluster-robust.

pub fn fit_with_cluster_folds( &self, data: &DmlData, splits: &[Vec<ClusterFold>], ) -> Result<DmlFit>

Fit clustered data with explicit cluster folds, one Vec<ClusterFold> per repetition.

pub fn sensitivity_benchmark( &self, data: &DmlData, long: &DmlFit, benchmarking_set: &[usize], ) -> Result<SensitivityBenchmark>

Sensitivity benchmark for the covariate columns benchmarking_set: refits this model without them (with the same sample splitting, so long must come from fit with the current settings) and compares it with long.

pub fn fit_with_folds( &self, data: &DmlData, splits: &[Vec<Fold>], ) -> Result<DmlFit>

Fit with caller-supplied splits, one Vec<Fold> per repetition (e.g. to reproduce another implementation exactly).

Trait Implementations

impl LinearScoreModel for Apo

fn name(&self) -> String

Label for summaries, e.g. "PLR (partialling out)".

fn validate(&self, data: &DmlData) -> Result<()>

Reject data the model cannot handle (called once before fitting).

fn strata(&self, data: &DmlData) -> Option<Vec<usize>>

Strata for the default sample splits (e.g. treatment levels), so each fold holds about the same share of every stratum. None (the default) draws plain K-fold splits.

fn estimate_score( &self, input: &ScoreInput<'_>, folds: &[Fold], ) -> Result<ScoreEstimate>

Cross-fit the nuisances on folds and return the score elements.