tgrad: Gradient of function to optimize over Z in EM step.

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

Description

Gradient of function to optimize over Z in EM step.

Usage

tgrad(Z_old, sig_diag, Y, alpha, Tkj, a_seq, b_seq, nu)

Arguments

Z_old	A vector of numerics. The current value of Z.
sig_diag	A vector of length p containing the variances of the observations.
Y	A matrix of dimension p by 1. These are the observed regression coefficients of the observed variables.
alpha	A matrix. This is of dimension p by k and are the coefficients to the confounding variables.
Tkj	A matrix of numerics. The weights from pi_new.
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.
nu	A positive numeric. The degrees of freedom of the t-distribution.

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