Struct TestResult 

pub struct TestResult {
    pub statistic: f64,
    pub p_value: f64,
    pub log_p_value: Option<f64>,
    pub df: Option<f64>,
    pub effect_size: Option<f64>,
}

The outcome of a hypothesis test: its statistic, p-value, and — where the test defines them — degrees of freedom and an effect size.

df and effect_size are None for tests that define no such quantity (e.g. Shapiro–Wilk, Fisher exact), matching the reference’s contract rather than emitting a misleading numeric placeholder.

log_p_value is the natural log of the p-value (ln(p_value), the scipy.stats logsf/logcdf convention), populated for the tests whose null is a continuous distribution with a numerically-stable log tail (the t-tests, ANOVA/F, and the chi-squared-routed tests). It stays finite in the extreme tail where the linear Self::p_value underflows to 0.0. It is None for tests that report no continuous-tail p-value in log space (e.g. the exact rank tests and Shapiro–Wilk); Self::p_value is unchanged regardless.

Fields

statistic: f64

The test statistic (χ², t, F, U, …) — its meaning is per-test.

p_value: f64

The p-value in [0, 1] for the test’s selected alternative.

log_p_value: Option<f64>

ln(p_value), finite in the extreme tail where p_value underflows, or None for tests with no log-space p-value path.

df: Option<f64>

Degrees of freedom, or None when the test defines none.

effect_size: Option<f64>

The effect size (Cramér’s V, η², rank-biserial, …), or None.

Trait Implementations

impl Clone for TestResult

fn clone(&self) -> TestResult

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TestResult

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

Formats the value using the given formatter.

impl PartialEq for TestResult

fn eq(&self, other: &TestResult) -> 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 StructuralPartialEq for TestResult