update_classes_dp function

Dirichlet process-based update of latent classes

This function updates the latent classes based on a Dirichlet process.

update_classes_dp(
  Cmax,
  beta,
  z,
  b,
  Omega,
  delta,
  xi,
  D,
  nu,
  Theta,
  s_desc = TRUE
)

Arguments

• Cmax: The maximum number of classes.
• beta: The matrix of the decision-maker specific coefficient vectors of dimension P_r x N. Set to NA if P_r = 0.
• z: The vector of the allocation variables of length N. Set to NA if P_r = 0.
• b: The matrix of class means as columns of dimension P_r x C. Set to NA if P_r = 0.
• Omega: The matrix of class covariance matrices as columns of dimension P_r*P_r x C. Set to NA if P_r = 0.
• delta: A numeric for the concentration parameter vector rep(delta,C) of the Dirichlet prior for s. Per default, delta = 1. In case of Dirichlet process-based updates of the latent classes, delta = 0.1 per default.
• xi: The mean vector of length P_r of the normal prior for each b_c. Per default, xi = numeric(P_r).
• D: The covariance matrix of dimension P_r x P_r of the normal prior for each b_c. Per default, D = diag(P_r).
• nu: The degrees of freedom (a natural number greater than P_r) of the Inverse Wishart prior for each Omega_c. Per default, nu = P_r + 2.
• Theta: The scale matrix of dimension P_r x P_r of the Inverse Wishart prior for each Omega_c. Per default, Theta = diag(P_r).
• s_desc: If TRUE, sort the classes in descending class weight.

Returns

A list of updated values for z, b, Omega, s, and C.

Details

To be added.

Examples

set.seed(1)
z <- c(rep(1,20),rep(2,30))
b <- matrix(c(1,1,1,-1), ncol=2)
Omega <- matrix(c(1,0.3,0.3,0.5,1,-0.3,-0.3,0.8), ncol=2)
beta <- sapply(z, function(z) rmvnorm(b[,z], matrix(Omega[,z],2,2)))
delta <- 1
xi <- numeric(2)
D <- diag(2)
nu <- 4
Theta <- diag(2)
RprobitB:::update_classes_dp(
  Cmax = 10, beta = beta, z = z, b = b, Omega = Omega,
  delta = delta, xi = xi, D = D, nu = nu, Theta = Theta
)