Struct BadDataReport 

pub struct BadDataReport {
    pub chi_squared: f64,
    pub degrees_of_freedom: usize,
    pub p_value: f64,
    pub suspects: Vec<Suspect>,
}

The outcome of a bad-data analysis.

Fields

chi_squared: f64

J = rᵀWr, the chi-squared statistic. Twice SeReport::objective, which carries the conventional ½.

degrees_of_freedom: usize

p_value: f64

Probability of seeing a J at least this large if every measurement were merely noisy. Small means the data is not merely noisy.

suspects: Vec<Suspect>

Measurements examined, worst first.

Implementations

impl BadDataReport

pub fn rejects_at(&self, significance: f64) -> bool

Whether the chi-squared test rejects at the given significance (0.05 is conventional).

Rejection says something is wrong, not which measurement — that is what suspects is for. A test that does not reject is also not a clean bill of health: a single moderate error, or several that partly cancel, can sit inside the threshold.

pub fn worst(&self) -> Option<Suspect>

The worst measurement, if any were examined.

Trait Implementations

impl Clone for BadDataReport

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for BadDataReport

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

Formats the value using the given formatter.