MultiBatchModel2 {CNPBayes}R Documentation

Constructor for MultiBatchModel

Description

Initializes a MultiBatchModel, a container for storing data, parameters, and MCMC output for mixture models with batch- and component-specific means and variances.

Usage

MultiBatchModel2(dat = numeric(), hp = HyperparametersMultiBatch(),
  mp = McmcParams(iter = 1000, thin = 10, burnin = 1000, nStarts = 4),
  batches = integer())

Arguments

dat

the data for the simulation.

hp

An object of class 'Hyperparameters' used to specify the hyperparameters of the model.

mp

An object of class 'McmcParams'

batches

an integer-vector of the different batches

Value

An object of class 'MultiBatchModel'

Examples

  model <- MultiBatchModel2(rnorm(10), batch=rep(1:2, each=5))
  set.seed(100)
  nbatch <- 3
  k <- 3
  means <- matrix(c(-2.1, -2, -1.95, -0.41, -0.4, -0.395, -0.1,
      0, 0.05), nbatch, k, byrow = FALSE)
  sds <- matrix(0.15, nbatch, k)
  sds[, 1] <- 0.3
  N <- 1000
  truth <- simulateBatchData(N = N, batch = rep(letters[1:3],
                                                length.out = N),
                             p = c(1/10, 1/5, 1 - 0.1 - 0.2),
                             theta = means,
                             sds = sds)

    truth <- simulateBatchData(N = 2500,
                               batch = rep(letters[1:3], length.out = 2500),
                               theta = means, sds = sds,
                               p = c(1/5, 1/3, 1 - 1/3 - 1/5))
    MultiBatchModel2(dat=y(truth), batches=batch(truth),
                     hp=hpList(k=3)[["MB"]])

[Package CNPBayes version 1.12.0 Index]