ZINB_one_gamma: Zero-Inflated Negative Binomial - One Gamma Component

In sidiwang/hgzips: hgzips

Description

This ZINB_one_gamma function finds hyperparameter estimates by implementing the Expectation-Maximization (EM) algorithm and zero-inflated negative binomial model with one gamma component. nlminb function is used to maximize the loglikelihood function.

Usage

ZINB_one_gamma(
  alpha,
  beta,
  omega,
  N,
  E,
  weight,
  iteration,
  Loglik = FALSE,
  zeroes = FALSE,
  N_star = 1
)

Arguments

alpha	initial shape parameter value of the gamma distribution for implementing the EM algprithm
beta	initial rate parameter value of the gamma distribution for implementing the EM algprithm
omega	initial weight for observing a true zero (according to zero-inflated poission distribution)
N	vector of Nij values
E	vector of Eij values
weight	set weight = rep(1, length(N)) if N and E are not squashed data, or input the weight vector corresponding to the squashed Nij vector.
iteration	number of EM algorithm iterations to run
Loglik	whether to return the loglikelihood of each iteration or not (TRUE or FALSE)
zeroes	A logical scalar specifying if zero counts should be included.
N_star	the minimum Nij count size to be used for hyperparameter estimation. If zeroes are included in Nij vector, please set N_star = NULL

Value

a list including the following: if Nij = 0 is included in the input dataset

• theta_EM Estimate of hyperparameters for each EM iteration

• llh logliklihood for each EM iteration (optional)

if the minimum Nij count size included in the input dataset is not 0"

• alpha Estimated alpha value

• beta Estimated beta value

• omega is not exported because the value of omega doesn't affect the estimation of lambda

See Also

openEBGM, nlminb

Examples

Nij = rnbinom(100, size = 2, prob = 0.3)
Eij = runif(100, 0, 2)
par_estimated = ZINB_one_gamma(0.2, 0.1, 0.33, Nij, Eij, rep(1, length(Nij)), iteration = 10, Loglik = TRUE, zeros = TRUE, N_star = 1)
par_estimated$theta_EM
par_estimated$Loglik

sidiwang/hgzips documentation built on Jan. 19, 2021, 4:09 p.m.