adalasso conducts adaptive lasso method to selection covariates by using glmnet. This function utilize cross-validation to find optimal lambda (lambda.min) and penalty factors for the adaptive lasso.

adalasso conducts adaptive lasso method to selection covariates by using glmnet. This function utilize cross-validation to find optimal lambda (lambda.min) and penalty factors for the adaptive lasso.

Usage

adalasso_refit(
  x,
  y,
  intercept = TRUE,
  family = "gaussian",
  standardize = FALSE,
  refit = TRUE,
  parallel = FALSE,
  ...
)

Arguments

x: The input matrix with dimensions (nobs) and (nvars). It has n rows (obs), and p columns (number of covariates).
y: Response variable. Now, SSCI only supports family="gaussian" with continuous respones y.
intercept: Should intercept(s) be fitted (default=TRUE) or set to zero (FALSE).
family: Response type. Either a character string representing one of the built-in families, or else a glm() family object.
standardize: logical argument whether conduct standardization.
refit: logical. Should conduct a selection + refitting procedure? TRUE, the default, asks the algorithm to conduct the refitting after variable selection.
parallel: If TRUE, use parallel foreach to fit models on bootstrap samples. Must register parallel beforehand, such as doParallel or others. See the example below.
...: Additional optional arguments.

Value

A list with three components: coefficients (estimates), sel_vars (selected variables), and nz (indexes of non-zero coefficients).