Struct ProfileChart 

#[non_exhaustive]
pub struct ProfileChart {
    pub reference_fosr: FosrResult,
    pub beta_fpca: FpcaResult,
    pub eigenvalues: Vec<f64>,
    pub t2_limit: ControlLimit,
    pub lag1_autocorrelation: f64,
    pub effective_n_windows: f64,
    pub config: ProfileMonitorConfig,
}

Phase I profile monitoring chart.

When effective_n_windows is much smaller than the actual number of windows, the chi-squared UCL may need adjustment. A practical approach: multiply the UCL by effective_n_windows / n_windows to approximate a Bonferroni-like correction.

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.

reference_fosr: FosrResult

FOSR result from the full reference data.

beta_fpca: FpcaResult

FPCA of the rolling beta coefficient functions.

eigenvalues: Vec<f64>

Eigenvalues: sv² / (n_windows - 1).

t2_limit: ControlLimit

T-squared control limit for beta monitoring.

lag1_autocorrelation: f64

Lag-1 autocorrelation of the Phase I T-squared statistics from rolling windows. High values (> 0.5) indicate serial correlation from window overlap.

Computed from the Phase I T-squared statistic sequence. Values |rho_1| > 0.3 indicate substantial serial correlation; effective_n_windows will be notably reduced. The estimator uses the unbiased sample variance (n-1 denominator) for both variance and covariance terms.

effective_n_windows: f64

Effective number of independent windows (Bartlett correction for overlap). When step_size < window_size, consecutive windows overlap and are correlated, reducing the effective degrees of freedom.

Computed as n_eff = n_windows / (1 + 2|rho_1|), which is the Bartlett (1946, section 3) formula for AR(1) processes. For overlap fraction f = 1 - step_size/window_size, the lag-1 autocorrelation is approximately f, so n_eff ~ n_windows / (1 + 2f). This is conservative (underestimates n_eff) for non-AR(1) dependence structures.

Use this to assess whether the chi-squared UCL is reliable. When effective_n_windows < 20, consider widening the control limit or using bootstrap limits instead.

config: ProfileMonitorConfig

Configuration used.

Trait Implementations

impl Clone for ProfileChart

fn clone(&self) -> ProfileChart

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ProfileChart

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

Formats the value using the given formatter.

impl PartialEq for ProfileChart

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