unif_update_z: Runs a few newton steps to update Z given scale_val.

In dcgerard/succotashr: Surrogate and Confounder Correction Occuring Together with Adaptive Shrinkage

Description

Runs a few newton steps to update Z given scale_val.

Usage

unif_update_z(Y, sig_diag, alpha, lambda, a_seq, b_seq, pi_new, Tkj, Z_old,
  llike_old, tol = 10^-3, newt_itermax = 10, print_ziter = FALSE,
  scale_val = 1)

Arguments

Y	A matrix of dimension p by 1. These are the observed regression coefficients of the observed variables.
sig_diag	A vector of length p containing the variances of the observations.
alpha	A matrix. This is of dimension p by k and are the coefficients to the confounding variables.
lambda	A vector. This is a length M vector with the regularization parameters for the mixing proportions.
a_seq	A vector of negative numerics containing the left endpoints of the mixing uniforms.
b_seq	A vector of positiv numerics containing the right endpoints of the mixing uniforms.
pi_new	A vector of numerics. The current estimates of of the mixing proportions.
Tkj	A matrix of numerics. The T matrix.
Z_old	A vector of numerics. The old confounders.
llike_old	The old log-likelihood
tol	A positive numeric. The stopping criterion for Newton's method in updating Z.
newt_itermax	A positive integer. The maximum number of Newton steps to perform in updating Z.
print_ziter	A logical. Should we we print each iteration of the Z optimization?
scale_val	A positive numeric. The variance inflation parameter.

dcgerard/succotashr documentation built on May 15, 2019, 1:25 a.m.