Struct SpmConfig 

pub struct SpmConfig {
    pub ncomp: usize,
    pub alpha: f64,
    pub tuning_fraction: f64,
    pub seed: u64,
}

Configuration for SPM chart construction.

Fields

ncomp: usize

Number of principal components to retain (default 5).

Typical range: 3–10. Use select_ncomp() for data-driven selection. More components capture finer structure but increase dimensionality of the monitoring statistic.

alpha: f64

Significance level for control limits (default 0.05).

tuning_fraction: f64

Fraction of data used for tuning/FPCA (default 0.5).

The remainder forms the calibration set for control limits. Default 0.5 balances FPCA estimation quality against control limit precision. With small datasets (n < 50), consider 0.6–0.7 to ensure adequate FPCA estimation.

The tuning/calibration split induces a bias-variance trade-off: a larger tuning fraction yields better FPCA eigenfunction estimates but less precise control limits. The optimal split depends on the eigenvalue decay rate — fast decay (smooth processes) favors allocating more data to calibration, while slow decay (rough processes) favors more tuning data for stable FPCA estimation.

seed: u64

Random seed for data splitting (default 42).

Trait Implementations

impl Clone for SpmConfig

fn clone(&self) -> SpmConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SpmConfig

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

Formats the value using the given formatter.

impl Default for SpmConfig

fn default() -> Self

Returns the “default value” for a type.

impl PartialEq for SpmConfig

fn eq(&self, other: &SpmConfig) -> 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 SpmConfig