get_beta_glmnet: Run CV glmnet

In stephenbates19/digitaltwins: Causal inference for SNPs

Description

Returns the fitted coefficients from a lasso fit after tuning the regularization parameter by cross-validation. Intended for internal use with the linear_crt function.

Usage

get_beta_glmnet(X, Y, train_idx, family = "gaussian", s = "lambda.min",
  parallel = FALSE)

Arguments

X	and n by p matrix
Y	a response vector of length n
train_idx	a set of indices to train on
family	type of regression, either "gaussian" or "binomial"
s	coefficient vector to return. either "lambda.min" or "lambda.1se"
parallel	set to TRUE to run CV in parallel. Must initialize DoMC or DoParallel prior to execution.

Value

Fitted coefficients, a vector of length p + 1. First coordinate is the intercept.

stephenbates19/digitaltwins documentation built on Feb. 25, 2020, 12:41 a.m.