update_scale_p_mn: Update conditional expectation of prior probabilities of...

In jmleach-bst/ssnet: Fit Spike-and-Slab Elastic Net GLM With Spatial Priors on Parameters

Update conditional expectation of prior probabilities of inclusion at each iteration.

Description

Specifically adresses group selection where conditional expecation depends on vector of parameters, not a single scalar parameter value, i.e., this was specifically developed for our multinomial extension of spike-and-slab EN GLMs.

Usage

update_scale_p_mn(b0, ss, theta, alpha, print_out = FALSE)

Arguments

b0	A list. The length of the list should be equal to the total number of predictors, and each element should be a vector of parameter estimates corresponding to each.
ss	A vector of spike and slab prior scales, respectively.
theta	The current estimate of prior probabilities of inclusion.
alpha	A scalar value between 0 and 1 determining the compromise between the Ridge and Lasso models. When alpha = 1 reduces to the Lasso, and when alpha = 0 reduces to Ridge.
print_out	When TRUE prints intermediate output.

Value

A list whose first element is a vector of updated scale parameters for each parameter and whose second element is a vector of updated conditional expectations of prior probabilities of model inclusion.

Note

This function is a modified version of update_scale_p() from the R package BhGLM.

jmleach-bst/ssnet documentation built on March 4, 2024, 5:04 p.m.