estNBparams: A function to estimate the taxon-wise NB-params

In RCM: Fit row-column association models with the negative binomial distribution for the microbiome

Description

A function to estimate the taxon-wise NB-params

Usage

estNBparams(
  design,
  thetas,
  muMarg,
  psi,
  X,
  nleqslv.control,
  ncols,
  initParam,
  v,
  dynamic = FALSE,
  envRange,
  allowMissingness,
  naId
)

Arguments

design	an n-by-v design matrix
thetas	a vector of dispersion parameters of length p
muMarg	an offset matrix
psi	a scalar, the importance parameter
X	the data matrix
nleqslv.control	a list of control elements, passed on to nleqslv()
ncols	an integer, the number of columns of X
initParam	a v-by-p matrix of initial parameter estimates
v	an integer, the number of parameters per taxon
dynamic	a boolean, should response function be determined dynamically? See details
envRange	a vector of length 2, giving the range of observed environmental scores
allowMissingness	A boolean, are missing values present
naId	The numeric index of the missing values in X If dynamic is TRUE, quadratic response functions are fitted for every taxon. If the optimum falls outside of the observed range of environmental scores, a linear response function is fitted instead

Value

a v-by-p matrix of parameters of the response function

RCM documentation built on Nov. 8, 2020, 5:22 p.m.