Struct FitnessEstimate 

pub struct FitnessEstimate {
    pub mean: f64,
    pub variance: f64,
    pub ci_lower: f64,
    pub ci_upper: f64,
    pub observation_count: usize,
}

Full fitness estimate with uncertainty quantification

Represents a fitness value along with its statistical uncertainty, including variance and confidence intervals. This enables informed decision-making about which candidates need more evaluation.

Example

use fugue_evo::interactive::uncertainty::FitnessEstimate;

let estimate = FitnessEstimate::new(7.5, 0.25, 10);
println!("Fitness: {:.2} ± {:.2}", estimate.mean, estimate.std_error());
println!("95% CI: [{:.2}, {:.2}]", estimate.ci_lower, estimate.ci_upper);

Fields

mean: f64

Point estimate (mean fitness)

variance: f64

Variance of the estimate

ci_lower: f64

Lower bound of confidence interval (default 95%)

ci_upper: f64

Upper bound of confidence interval

observation_count: usize

Number of observations contributing to this estimate

Implementations

impl FitnessEstimate

pub fn new(mean: f64, variance: f64, observation_count: usize) -> Self

Create a new fitness estimate from mean and variance

Automatically computes 95% confidence intervals from the variance.

Arguments

• mean - Point estimate of fitness
• variance - Variance of the estimate (not the population variance)
• observation_count - Number of observations used to compute the estimate

pub fn with_confidence( mean: f64, variance: f64, observation_count: usize, z_score: f64, ) -> Self

Create estimate with custom confidence level

Arguments

• mean - Point estimate
• variance - Variance of the estimate
• observation_count - Number of observations
• z_score - Z-score for desired confidence level (e.g., 1.96 for 95%, 2.576 for 99%)

pub fn uninformative(default_mean: f64) -> Self

Create an uninformative estimate (infinite variance)

Used for candidates with no evaluations.

pub fn std_error(&self) -> f64

Standard error (sqrt of variance)

pub fn ci_width(&self) -> f64

Width of the confidence interval

pub fn ci_contains(&self, value: f64) -> bool

Check if confidence interval contains a value

pub fn ci_overlaps(&self, other: &FitnessEstimate) -> bool

Check if this estimate overlaps with another’s confidence interval

pub fn significantly_better_than(&self, other: &FitnessEstimate) -> bool

Check if this estimate is significantly better than another

Returns true if the lower bound of this estimate’s CI is above the upper bound of the other’s CI.

pub fn is_uncertain(&self, min_observations: usize) -> bool

Check if this estimate has high uncertainty (needs more data)

Returns true if variance is infinite or observation count is below threshold.

pub fn coefficient_of_variation(&self) -> Option<f64>

Coefficient of variation (relative uncertainty)

Returns None if mean is zero to avoid division by zero.

pub fn merge(&self, other: &FitnessEstimate) -> FitnessEstimate

Merge two independent estimates (weighted by inverse variance)

Combines two estimates using inverse-variance weighting, which is optimal for independent normal estimates.

Trait Implementations

impl Clone for FitnessEstimate

fn clone(&self) -> FitnessEstimate

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FitnessEstimate

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

Formats the value using the given formatter.

impl Default for FitnessEstimate

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for FitnessEstimate

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for FitnessEstimate

fn eq(&self, other: &FitnessEstimate) -> 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 Serialize for FitnessEstimate

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 FitnessEstimate