respFunScoreMat: Derivative of the Lagrangian of the parametric response...

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

Description

Derivative of the Lagrangian of the parametric response function

Usage

respFunScoreMat(
  betas,
  X,
  reg,
  thetaMat,
  muMarg,
  psi,
  p,
  v,
  allowMissingness,
  naId,
  ...
)

Arguments

betas	a vector of length (deg+1)*(p+1) with regression parameters with deg the degree of the response function and the lagrangian multipliers
X	the nxp data matrix
reg	a matrix of regressors with the dimension nx(deg+1)
thetaMat	The n-by-p matrix with dispersion parameters
muMarg	offset matrix of size nxp
psi	a scalar, the importance parameter
p	an integer, the number of taxa
v	an integer, one plus the degree of the response function
allowMissingness	A boolean, are missing values present
naId	The numeric index of the missing values in X
...	further arguments passed on to the jacobian The parameters are restricted to be normalized, i.e. all squared intercepts, first order and second order parameters sum to 1

Value

The evaluation of the score functions, a vector of length (p+1)* (deg+1)

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