Struct PoissonResult 

pub struct PoissonResult {
    pub nll: f64,
    pub iterations: usize,
    pub converged: bool,
    pub params: Vec<f64>,
    pub covariance: Option<FlatMatrix>,
    pub uncertainties: Option<Vec<f64>>,
}

Result of Poisson-likelihood optimization.

Fields

nll: f64

Final negative log-likelihood.

iterations: usize

Number of iterations taken.

converged: bool

Whether the optimizer converged.

params: Vec<f64>

Final parameter values (all parameters, including fixed).

covariance: Option<FlatMatrix>

Local covariance estimate from the inverse Fisher information matrix at the converged parameters: F⁻¹ = (J^T H J)⁻¹ where H = diag(obs/model²) is the Poisson Hessian.

This is a local curvature estimate, NOT a Bayesian posterior. When an analytical Jacobian is available, it is used directly. Otherwise a finite-difference Jacobian is computed as fallback. None when the fit did not converge, the Fisher matrix is singular, or covariance computation is disabled via config.

uncertainties: Option<Vec<f64>>

Standard errors of free parameters: √diag(F⁻¹). None when covariance is not available.

Trait Implementations

impl Clone for PoissonResult

fn clone(&self) -> PoissonResult

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PoissonResult

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

Formats the value using the given formatter.