Struct FrccConfig 

pub struct FrccConfig {
    pub ncomp: usize,
    pub fosr_lambda: f64,
    pub alpha: f64,
    pub tuning_fraction: f64,
    pub seed: u64,
    pub min_r_squared: f64,
}

Configuration for FRCC chart construction.

Fields

ncomp: usize

Number of principal components for residual FPCA (default 5).

fosr_lambda: f64

FOSR smoothing parameter; controls roughness penalty on β(t) (default 1e-4). Larger values produce smoother coefficient functions. Typical range: [1e-6, 1e-2]. Use cross-validation if unsure.

alpha: f64

Significance level (default 0.05).

tuning_fraction: f64

Fraction of data for tuning (default 0.5).

Must be in (0, 1). The tuning set is used for FOSR fitting and R-squared assessment; the calibration set (1 - tuning_fraction) is used for FPCA and control limit estimation. Larger tuning fractions give more stable FOSR estimates but fewer calibration observations for control limits. For n < 50, consider tuning_fraction = 0.4 to ensure adequate calibration. For n > 200, tuning_fraction = 0.6 may improve FOSR stability.

seed: u64

Random seed (default 42).

min_r_squared: f64

Minimum FOSR R² required to proceed (default 0.1). If the FOSR model explains less than this fraction of variance, frcc_phase1 returns an error suggesting standard SPM instead.

Default 0.1 is a lenient threshold that catches only clearly useless models. For production use, consider 0.2–0.3. An R² of 0.3 means predictors explain 30% of functional variance — enough for meaningful covariate adjustment.

Trait Implementations

impl Clone for FrccConfig

fn clone(&self) -> FrccConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FrccConfig

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

Formats the value using the given formatter.

impl Default for FrccConfig

fn default() -> Self

Returns the “default value” for a type.

impl PartialEq for FrccConfig

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for FrccConfig