Enum LambdaChoice 

pub enum LambdaChoice {
    Fixed(f64),
    Gcv,
    Reml,
}

How to choose the smoothing parameter λ for the PEER estimator.

The default is LambdaChoice::Gcv which automatically selects λ by minimising the GCV score over a fixed internal log-spaced grid.

Variants

Fixed(f64)

Use this value verbatim; no grid search or EM is performed.

Gcv

Select λ by minimising the GCV score on a fixed 40-point log-spaced internal grid over [1e-6, 1e4]. Fully deterministic; ties resolve to the smaller grid index.

Reml

Estimate λ via a self-contained REML EM using the eigendecomposition of the penalty matrix Q (null space → fixed effect; range space → random effect b ∼ N(0, σ²_u I)). Returns λ = σ²_e / σ²_u. Fully deterministic; fixed initialisation and 100-iteration cap.

Trait Implementations

impl Clone for LambdaChoice

fn clone(&self) -> LambdaChoice

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LambdaChoice

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

Formats the value using the given formatter.

impl Default for LambdaChoice

fn default() -> LambdaChoice

Returns the “default value” for a type.

impl PartialEq for LambdaChoice

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for LambdaChoice