Struct BayesianShrinkagePrior 

pub struct BayesianShrinkagePrior {
    pub prior_mean: f64,
    pub prior_variance: f64,
}

Prior distribution parameters for Bayesian shrinkage estimation.

Uses a normal prior N(prior_mean, prior_variance) that pulls empirical estimates toward the prior when sample size is small or variance is high.

Fields

prior_mean: f64

Prior mean for the loss value.

prior_variance: f64

Prior variance (τ₀²) - controls how strongly we trust the prior. Smaller values mean stronger pull toward prior_mean.

Implementations

impl BayesianShrinkagePrior

pub const fn for_false_negative() -> Self

Default prior for false-negative loss (allowing incompatible operation).

pub const fn for_validate_cost() -> Self

Default prior for validation cost.

pub const fn for_false_positive() -> Self

Default prior for false-positive loss (rejecting compatible operation).

pub fn shrinkage_weight( &self, empirical_variance: f64, sample_count: usize, ) -> f64

Compute shrinkage weight given empirical variance and sample count.

w = τ₀² / (τ₀² + σ²/n)

When n is small or σ² is large, w is small (trust prior more). When n is large and σ² is small, w approaches 1 (trust data more).

pub fn posterior_mean( &self, empirical_mean: f64, empirical_variance: f64, sample_count: usize, ) -> f64

Compute the posterior mean using shrinkage.

μ_posterior = w * ȳ + (1-w) * μ₀

Trait Implementations

impl Clone for BayesianShrinkagePrior

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Copy for BayesianShrinkagePrior

impl Debug for BayesianShrinkagePrior

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq for BayesianShrinkagePrior

fn eq(&self, other: &Self) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for BayesianShrinkagePrior