preseqR.ztnb.em {preseqR} | R Documentation |
Fitting a zero-truncated negative binomial distribution
Description
preseqR.ztnb.em
fits a zero-truncated negative binomial (ZTNB)
distribution to the initial sample.
Since the species with zero observations are missed in the sample, an
EM algorithm is used to estimate the parameters assuming the number of
individuals for each species follows a Negative Binomial distribution
with the zero counts as a missing latent data.
Usage
preseqR.ztnb.em(n, size = SIZE.INIT, mu = MU.INIT)
Arguments
n |
A two-column matrix.
The first column is the frequency |
size |
A positive double setting the initial value of the parameter |
mu |
A positive double setting the initial value of the parameter |
Details
See the supplement of Daley and Smith (2013).
Value
size |
The estimate of the parameter |
mu |
The estimate of the parameter |
loglik |
Log-likelihood under estimated ZTNB. |
Author(s)
Chao Deng
Examples
## load library
library(preseqR)
## import data
data(FisherButterfly)
## print the parameters of a fitting negative binomial distribution
preseqR.ztnb.em(FisherButterfly)