Struct BinomialMultiFitOutputs 

pub struct BinomialMultiFitOutputs {
    pub coefficients: Array2<f64>,
    pub fitted_probabilities: Array2<f64>,
    pub iterations: usize,
    pub converged: bool,
    pub penalized_neg_log_likelihood: f64,
    pub deviance: f64,
}

Outputs of fit_penalized_binomial_multi.

Fields

coefficients: Array2<f64>

Coefficient matrix, shape (P, K) (column a is β_a).

fitted_probabilities: Array2<f64>

Fitted probabilities μ_{n,a} = σ((X β_a)_n), shape (N, K).

iterations: usize

Number of joint Newton iterations executed (including the final step that satisfied the tolerance). The K columns share the design and are fitted by a single coupled damped-Newton loop over the block-diagonal penalized Hessian, so there is one iteration count for the whole solve.

converged: bool

true if the relative-step test was satisfied before max_iter.

penalized_neg_log_likelihood: f64

Penalized negative log-likelihood at the returned β̂: −log L(β̂) + ½ Σ_a λ_a · β̂_aᵀ S β̂_a.

deviance: f64

Unpenalized deviance −2 log L(β̂) for diagnostic reporting.

Trait Implementations

impl Clone for BinomialMultiFitOutputs

fn clone(&self) -> BinomialMultiFitOutputs

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for BinomialMultiFitOutputs

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

Formats the value using the given formatter.