categorical_logit_rng()

template<class RNG >

int stan::math::categorical_logit_rng ( const Eigen::VectorXd &  beta, RNG &  rng  )

inline

Return a draw from a Categorical distribution given a vector of unnormalized log probabilities and a pseudo-random number generator.

In the case of finite and -inf values this is a convenience wrapper around categorical_rng(softmax(beta), rng). Entries of beta equal to -inf have zero probability; if any entries are +inf, probability is split evenly among them. These are the limits of softmax: as beta[n] -> -inf, softmax(beta)[n] -> 0, and if k entries -> +inf at the same rate, each has probability 1/k.

Template Parameters

RNG	Type of pseudo-random number generator.

Parameters

beta	Vector of unnormalized log probabilities.
rng	Pseudo-random number generator.

Returns

Categorical random variate

Exceptions

std::domain_error	if beta contains NaN
std::domain_error	if every entry of beta is negative infinity

Definition at line 36 of file categorical_logit_rng.hpp.