Struct ChiSquared 

pub struct ChiSquared { /* private fields */ }

Chi-squared distribution.

The chi-squared distribution with k degrees of freedom is a special case of the gamma distribution: χ²(k) = Gamma(k/2, 1/2).

f(x) = (1 / (2^(k/2) Γ(k/2))) x^(k/2-1) exp(-x/2) for x > 0

Examples

use solvr::stats::{ChiSquared, ContinuousDistribution, Distribution};

let chi2 = ChiSquared::new(5)?;
println!("Mean: {}", chi2.mean());
println!("95th percentile: {}", chi2.ppf(0.95)?);

Implementations

impl ChiSquared

pub fn new(k: u64) -> StatsResult<Self>

Create a new chi-squared distribution with k degrees of freedom.

Arguments

• k - Degrees of freedom (must be positive)

Errors

Returns an error if k is not positive.

pub fn new_f64(k: f64) -> StatsResult<Self>

Create from a floating-point degrees of freedom (for generalization).

pub fn df(&self) -> f64

Get the degrees of freedom.

Trait Implementations

impl Clone for ChiSquared

fn clone(&self) -> ChiSquared

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl ContinuousDistribution for ChiSquared

fn pdf(&self, x: f64) -> f64

Probability density function.

fn log_pdf(&self, x: f64) -> f64

Log of the probability density function.

fn cdf(&self, x: f64) -> f64

Cumulative distribution function.

fn sf(&self, x: f64) -> f64

Survival function.

fn ppf(&self, p: f64) -> StatsResult<f64>

Percent point function (quantile function / inverse CDF).

fn pdf_tensor<R: Runtime, C>( &self, x: &Tensor<R>, client: &C, ) -> Result<Tensor<R>>

where C: TensorOps<R> + ScalarOps<R> + RuntimeClient<R>,

Batch probability density function.

fn log_pdf_tensor<R: Runtime, C>( &self, x: &Tensor<R>, client: &C, ) -> Result<Tensor<R>>

where C: TensorOps<R> + ScalarOps<R> + RuntimeClient<R>,

Batch log probability density function.

fn cdf_tensor<R: Runtime, C>( &self, x: &Tensor<R>, client: &C, ) -> Result<Tensor<R>>

where C: TensorOps<R> + ScalarOps<R> + SpecialFunctions<R> + RuntimeClient<R>,

Batch cumulative distribution function.

fn sf_tensor<R: Runtime, C>( &self, x: &Tensor<R>, client: &C, ) -> Result<Tensor<R>>

where C: TensorOps<R> + ScalarOps<R> + SpecialFunctions<R> + RuntimeClient<R>,

Batch survival function.

fn log_cdf_tensor<R: Runtime, C>( &self, x: &Tensor<R>, client: &C, ) -> Result<Tensor<R>>

where C: TensorOps<R> + ScalarOps<R> + SpecialFunctions<R> + RuntimeClient<R>,

Batch log cumulative distribution function.

fn ppf_tensor<R: Runtime, C>( &self, p: &Tensor<R>, client: &C, ) -> Result<Tensor<R>>

where C: TensorOps<R> + ScalarOps<R> + SpecialFunctions<R> + RuntimeClient<R>,

Batch percent point function (quantile function / inverse CDF).

fn isf_tensor<R: Runtime, C>( &self, p: &Tensor<R>, client: &C, ) -> Result<Tensor<R>>

where C: TensorOps<R> + ScalarOps<R> + SpecialFunctions<R> + RuntimeClient<R>,

Batch inverse survival function.

fn log_cdf(&self, x: f64) -> f64

Log of the cumulative distribution function.

fn isf(&self, p: f64) -> StatsResult<f64>

Inverse survival function.

fn interval(&self, alpha: f64) -> StatsResult<(f64, f64)>

Interval containing a given probability mass.

impl Debug for ChiSquared

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

Formats the value using the given formatter.

impl Distribution for ChiSquared

fn mean(&self) -> f64

Get the mean of the distribution.

fn var(&self) -> f64

Get the variance of the distribution.

fn entropy(&self) -> f64

Get the Shannon entropy of the distribution (in nats).

fn median(&self) -> f64

Get the median of the distribution.

fn mode(&self) -> f64

Get the mode of the distribution.

fn skewness(&self) -> f64

Get the skewness of the distribution.

fn kurtosis(&self) -> f64

Get the excess kurtosis of the distribution.

fn std(&self) -> f64

Get the standard deviation of the distribution.

impl Copy for ChiSquared