CUE_vec_J_bin: Newton Raphson Steps for plmed fitting

In ohines/plmed: Causal Mediation Effects For Partially Linear Models

Description

CUE_vec_J_bin Generates newton raphson steps for the plmed fitting functions.

Usage

CUE_vec_J_bin(
  par,
  X,
  M,
  Y,
  Z,
  Xfam = binomial(),
  method = "G",
  weights = rep(1, N),
  med_prop = NULL,
  Sig = NULL
)

Arguments

par	vector containing beta and augmented nuisance parameters, optionally with a lagrange multiplier the final componenet.
X	Vector of exposures
M	Vector of mediators
Y	Vector of outcomes
Z	Design matrix of confounder models
method	The method to be used. See ‘Details’.
med_prop	Hypothesised mediation proportion for constrained optimisation. Requires method 'CUE' or 'Two-step'.
Sig	Constant covariance matrix must be prespecified when using 'Two-step' method.

Value

A list containing the newton-raphson step for use with newton_raph as well as variance and score estimates.

ohines/plmed documentation built on Jan. 9, 2021, 11:59 a.m.