dNBllrow: A score function of the NB for the row scores

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

Description

A score function of the NB for the row scores

Usage

dNBllrow(
  beta,
  X,
  reg,
  thetas,
  muMarg,
  k,
  n,
  p,
  rowWeights,
  nLambda,
  rMatK,
  allowMissingness,
  naId,
  ...
)

Arguments

beta	a vector of of length n + k +1 regression parameters to optimize
X	the data matrix of dimensions nxp
reg	a 1xp regressor matrix: outer product of column scores and psis
thetas	nxp matrix with the dispersion parameters (converted to matrix for numeric reasons)
muMarg	an nxp offset matrix
k	a scalar, the dimension of the RC solution
n	a scalar, the number of samples
p	a scalar, the number of taxa
rowWeights	a vector of length n, the weights used for the restrictions
nLambda	an integer, the number of lagrangian multipliers
rMatK	the lower dimension row scores
allowMissingness	A boolean, are missing values present
naId	The numeric index of the missing values in X
...	Other arguments passed on to the jacobian

Value

A vector of length n + k +1 with evaluations of the derivative of the lagrangian

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