Zero-Inflated Latent Dirichlet Allocation

Estimate a zinLDA model using Gibbs Sampling.

zinLDA(sampleTaxaMatrix, K, alpha, pi, a, b, runs = 500)

Arguments

sampleTaxaMatrix

object of class matrix with integer entries.
K

number of latent subcommunities.
alpha

positive scalar symmetric hyperparameter of the Dirichlet prior on theta.
pi

scalar symmetric zero-inflation probability of the ZIGD prior on beta.
a

positive scalar symmetric hyperparameter of the ZIGD prior on beta.
b

positive scalar symmetric hyperparameter of the ZIGD prior on beta.
runs

length of the MCMC chain.

Value

An object of class "zinLDA_gibbs" containing parameter estimates of theta, beta, and delta from each of the MCMC runs.