Skip to main content

RobustScatter

robust_rs::multivariate

Trait RobustScatter 

Source 
pub trait RobustScatter {
    // Required methods
    fn location(&self) -> &Array1<f64>;
    fn scatter(&self) -> &Array2<f64>;
    fn distances(&self) -> &Array1<f64>;

    // Provided methods
    fn distance_cutoff(&self, quantile: f64) -> f64 { ... }
    fn outliers(&self, quantile: f64) -> Vec<bool> { ... }
}
Expand description

Quantities every fitted robust covariance estimator can report, the multivariate counterpart of crate::estimator::RobustEstimator.

Required Methods§

Source

fn location(&self) -> &Array1<f64>

Robust location estimate μ̂.

Source

fn scatter(&self) -> &Array2<f64>

Robust scatter estimate Σ̂.

Source

fn distances(&self) -> &Array1<f64>

Robust Mahalanobis distances of the fitted rows.

Provided Methods§

Source

fn distance_cutoff(&self, quantile: f64) -> f64

The distance cutoff √χ²_{p, quantile} (e.g. quantile = 0.975) against which robust Mahalanobis distances are compared to flag outliers.

Source

fn outliers(&self, quantile: f64) -> Vec<bool>

Flag each fitted observation as an outlier when its robust distance exceeds distance_cutoff(quantile). Under a p-variate Gaussian the squared distances are χ²_p, so quantile = 0.975 flags ≈ 2.5% of clean data.

Dyn Compatibility§

This trait is dyn compatible.

In older versions of Rust, dyn compatibility was called "object safety".

Implementors§