Struct FastFmmConfig 

pub struct FastFmmConfig {
    pub smooth_window: usize,
    pub max_iter: usize,
    pub tol: f64,
    pub compute_inference: bool,
}

Configuration for fast_fmm.

No #[non_exhaustive] — callers may use struct-literal construction.

Fields

smooth_window: usize

Running-mean smoother window width along the grid axis (default: 3; 1 = no smoothing).

Divergence from R’s fastFMM

R’s fastFMM uses mgcv thin-plate splines for post-smoothing. fdars uses a running-mean smoother configured by this window width. Savitzky-Golay smoothing (better peak preservation) is a planned future improvement.

max_iter: usize

Maximum iterations for each per-gridpoint scalar mixed model (default: 30)

tol: f64

Convergence tolerance (default: 1e-8)

compute_inference: bool

Compute Wald t-statistics and pointwise p-values (default: true).

When false, t_stats is zero-filled and p_values is one-filled.

Divergence from R’s fastFMM

R uses a bootstrap for non-Gaussian inference. fdars provides Wald-only (standard-normal approximation) inference.

Trait Implementations

impl Clone for FastFmmConfig

fn clone(&self) -> FastFmmConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FastFmmConfig

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

Formats the value using the given formatter.

impl Default for FastFmmConfig

fn default() -> Self

Returns the “default value” for a type.

impl PartialEq for FastFmmConfig

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for FastFmmConfig