d_cmb_sample: Density for CMB random sample

In andrewraim/COMMultReg: Conway-Maxwell Multinomial Regression

Density for CMB random sample

Description

Compute individual density contributions for

X_i \sim \textrm{CMB}(m_i, p_i, ν_i), \quad i = 1, …, n.

Usage

d_cmb_sample(x, m, p, nu, take_log = FALSE)

Arguments

x	An n-dimensional vector of outcomes
m	An n-dimensional vector m_1, …, m_n
p	An n-dimensional vector of probability parameters p_1, …, p_n
nu	An n-dimensional vector of dispersion parameters ν_1, …, ν_n
take_log	TRUE or FALSE; if TRUE, return the value on the log-scale.

Value

A vector of density values f(x_1 \mid m_1, p_1, ν_1), …, f(x_n \mid m_n, p_n, ν_n), which may be on the log-scale and/or unnormalized according to input arguments. See cmb.

Examples

set.seed(1234)

n = 20
m = rep(10, n)

x = rnorm(n)
X = model.matrix(~ x)
beta = c(-1, 1)
p = plogis(X %*% beta)

w = rnorm(n)
W = model.matrix(~ w)
gamma = c(0.1, -0.1)
nu = X %*% gamma

y = numeric(n)
for (i in 1:n) {
    y[i] = r_cmb(1, m[i], p[i], nu[i])
}

d_cmb_sample(y, m, p, nu, take_log = TRUE)

andrewraim/COMMultReg documentation built on April 2, 2022, 11:04 p.m.