Struct DualPearson 

pub struct DualPearson {
    pub head_fraction: f64,
    pub head: PearsonIv,
    pub tail: PearsonIv,
}

A dual-Pearson profile R f_head + (1 - R) f_tail (Tasch et al. 1989).

Fields

head_fraction: f64

Fraction R in the head component, in [0, 1].

head: PearsonIv

Head component.

tail: PearsonIv

Tail component.

Implementations

impl DualPearson

pub fn pdf(&self, x: f64) -> f64

Probability density at x.

pub fn moments(&self) -> (f64, f64, f64, f64)

Mean, standard deviation, skewness and kurtosis of the mixture, from the components’ moments.

pub fn fit(hist: &Histogram) -> Result<DualPearsonFit, PearsonError>

Fit a dual-Pearson profile to a histogram (for example the depth histogram of stopped ions).

Method. The bins are rescaled to z = (x - μ) / σ with the mean and standard deviation of the in-range bin centres. The nine parameters are mapped to unconstrained variables (the logit of R; for each component the mean, ln σ, atanh(γ/4) and ln(β - β_IV(γ))), so every trial point is a valid pair of Pearson IV densities with |γ| < 4. The objective is the Neyman chi-square Σ (c_i - N P_i)^2 / max(c_i, 1) over the in-range bins, with P_i the model mass of bin i by three-point Gauss-Legendre quadrature and N the histogram total (so mass outside the range counts against the model). It is minimised by Nelder-Mead from two fixed starting points (a head at the overall moments with R = 0.9, and a tail one standard deviation deeper or shallower), each restarted once from its best point, with a cap of 6000 evaluations per run. The lowest objective wins; if the single Pearson IV from the histogram’s moments is better, it is returned as a degenerate dual (R = 1, both components equal).

The result is a deterministic function of the histogram (no random numbers, fixed iteration order). It is a least-squares representation, not a unique decomposition: different parameter sets can describe the same profile almost equally well, and the split into “head” and “tail” is only physically meaningful when the histogram resolves it.

Trait Implementations

impl Clone for DualPearson

fn clone(&self) -> DualPearson

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for DualPearson

impl Debug for DualPearson

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for DualPearson

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for DualPearson

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for DualPearson

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for DualPearson