Struct LpeerResult 

#[non_exhaustive]
pub struct LpeerResult {
    pub beta: Vec<f64>,
    pub intercept: f64,
    pub w_bar: Vec<f64>,
    pub fitted_values: Vec<f64>,
    pub sigma2_subject: f64,
    pub sigma2_resid: f64,
    pub n_subjects: usize,
    pub lambda: f64,
    pub penalty_type: PeerPenalty,
    pub gcv: Option<f64>,
    pub lambda_method: LambdaMethod,
}

Result of the lpeer longitudinal PEER estimator.

Carries the estimated coefficient function β(t), subject-level variance components, and the penalty configuration used — all on the argvals grid.

Both variance components are non-negative (clamped to a positive floor by famm::fit_scalar_mixed_model).

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

beta: Vec<f64>

Estimated coefficient function β(t), length m (on the argvals grid).

intercept: f64

Intercept (= ȳ, the mean of the response vector). Matches peer() convention.

w_bar: Vec<f64>

Column means of the Simpson-weighted design W[i,j] = data[(i,j)]·w[j], length m. Computed identically to peer() so predict reproduces training fitted_values exactly.

fitted_values: Vec<f64>

Fitted values ŷ_i (marginal, fixed-effect only), length n.

sigma2_subject: f64

Between-subject variance σ²_u (≥ 0). Estimated by REML EM inside famm::fit_scalar_mixed_model; clamped to a positive floor.

sigma2_resid: f64

Residual variance σ²_ε (≥ 0). Estimated by REML EM; clamped to a positive floor.

n_subjects: usize

Number of unique subjects derived from subject_map.

lambda: f64

Smoothing parameter λ that was used (from PeerConfig).

penalty_type: PeerPenalty

Penalty family that was used.

gcv: Option<f64>

GCV score at the selected λ. Some(score) when LambdaMethod::Gcv ran; None for LambdaMethod::Fixed or LambdaMethod::Reml.

lambda_method: LambdaMethod

Which λ-selection path ran.

Implementations

impl LpeerResult

pub fn predict( &self, new_data: &FdMatrix, argvals: &[f64], ) -> Result<Vec<f64>, FdarError>

Predict scalar responses for new functional observations (marginal prediction).

Applies the fitted coefficient function β(t) to new_data via the same formula as PeerResult::predict: new-subject random effect = 0 (marginal / fixed-effect-only prediction).

Self-consistency: re-passing the training data and argvals reproduces the training fitted_values to within 1e-9.

Errors

Returns FdarError::InvalidDimension when new_data.ncols() or argvals.len() does not equal the number of training grid points m.

Trait Implementations

impl Clone for LpeerResult

fn clone(&self) -> LpeerResult

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LpeerResult

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

Formats the value using the given formatter.

impl PartialEq for LpeerResult

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for LpeerResult