ml_by_group: 'ml_by_group' gets maximum likelihood estimates for groups of...

In emgthomas/moretrees_pkg: Multi-Outcome Regression with Tree-Structured Shrinkage

Description

ml_by_group gets maximum likelihood estimates for groups of outcomes.

Usage

ml_by_group(X, W = NULL, y, outcomes, outcome_groups, return_ci = TRUE,
  ci_level, family, return_theta = FALSE)

Arguments

X	An n x K matrix of exposure data, where K is the dimension of the exposure.
W	Matrix of covariates of dimension n x m.
y	Vector of length n containing outcomes data. If family = "bernoulli", y must be an integer vector where 1 = success, 0 = failure. If family = "gaussian", y must be a numeric vector containing continuous data.
outcomes	Character vector specifying which outcomes the rows of X and W correspond to.
outcome_groups	A list of length G, where each element is a character vector indiciating which outcomes belong to that group.
return_ci	Get confidence intervals? Default = TRUE
ci_level	A number between 0 and 1 giving the desired credible interval. For example, ci_level = 0.95 (the default) returns a 95% credible interval.
family	A string specifying the distribution of the outcomes: either "bernoulli" (for classification) or "gaussian" (for regression)
return_theta	Return ML estimates for theta? Default = FALSE

Value

A list containing the following elements: 1. estimated coefficients and credible intervals for beta; 2. estimated coefficients and credible intervals for theta.

See Also

Other Processing model output: moretrees_compute_betas, moretrees_compute_thetas

emgthomas/moretrees_pkg documentation built on June 20, 2020, 6:13 p.m.