Trait rv::traits::ConjugatePrior

pub trait ConjugatePrior<X, Fx>: Rv<Fx> where
    Fx: Rv<X> + HasSuffStat<X>, {
    type Posterior: Rv<Fx>;
    fn posterior(&self, x: &DataOrSuffStat<X, Fx>) -> Self::Posterior;
    fn ln_m(&self, x: &DataOrSuffStat<X, Fx>) -> f64;
    fn ln_pp(&self, y: &X, x: &DataOrSuffStat<X, Fx>) -> f64;

    fn m(&self, x: &DataOrSuffStat<X, Fx>) -> f64 { ... }
    fn pp(&self, y: &X, x: &DataOrSuffStat<X, Fx>) -> f64 { ... }
}

A prior on Fx that induces a posterior that is the same form as the prior

Associated Types

type Posterior: Rv<Fx>

Required Methods

fn posterior(&self, x: &DataOrSuffStat<X, Fx>) -> Self::Posterior

Computes the posterior distribution from the data

fn ln_m(&self, x: &DataOrSuffStat<X, Fx>) -> f64

Log marginal likelihood

fn ln_pp(&self, y: &X, x: &DataOrSuffStat<X, Fx>) -> f64

Log posterior predictive of y given x

Provided Methods

fn m(&self, x: &DataOrSuffStat<X, Fx>) -> f64

Marginal likelihood of x

fn pp(&self, y: &X, x: &DataOrSuffStat<X, Fx>) -> f64

Posterior Predictive distribution

Implementors

• impl ConjugatePrior<bool, Bernoulli> for Beta type Posterior = Self;

• impl ConjugatePrior<u8, Bernoulli> for Beta type Posterior = Self;

• impl ConjugatePrior<u16, Bernoulli> for Beta type Posterior = Self;

• impl ConjugatePrior<u32, Bernoulli> for Beta type Posterior = Self;

• impl ConjugatePrior<u64, Bernoulli> for Beta type Posterior = Self;

• impl ConjugatePrior<usize, Bernoulli> for Beta type Posterior = Self;

• impl ConjugatePrior<i8, Bernoulli> for Beta type Posterior = Self;

• impl ConjugatePrior<i16, Bernoulli> for Beta type Posterior = Self;

• impl ConjugatePrior<i32, Bernoulli> for Beta type Posterior = Self;

• impl ConjugatePrior<i64, Bernoulli> for Beta type Posterior = Self;

• impl ConjugatePrior<isize, Bernoulli> for Beta type Posterior = Self;

• impl<X: CategoricalDatum> ConjugatePrior<X, Categorical> for SymmetricDirichlet type Posterior = Dirichlet;

• impl<X: CategoricalDatum> ConjugatePrior<X, Categorical> for Dirichlet type Posterior = Self;

• impl ConjugatePrior<f64, Gaussian> for NormalGamma type Posterior = Self;

• impl ConjugatePrior<DVector<f64>, MvGaussian> for NormalInvWishart type Posterior = NormalInvWishart;