ProbitLasso: Title Lasso and Adaptive Lasso Probit Regression

In EOgundimu300/HeckmanSelect: Regularization method for binary Heckman selection model

Description

Title Lasso and Adaptive Lasso Probit Regression

Usage

ProbitLasso(
  formula,
  data = sys.frame(sys.parent()),
  lambda = NULL,
  allowParallel = FALSE,
  penalty = c("LASSO", "ALASSO"),
  crit = c("bic", "aic", "gcv"),
  ...
)

Arguments

formula	model formula for probit regression. This is the outcome model when the missing data is deleted
data	data matrix containing the outcome and covariates for probit regression
lambda	shrinkage parameter, both scalar and vector are acceptable When lambda=NULL, the internal vector of Lambda is used
allowParallel	If true, the "doParallel" package is invoked
penalty	can be ALASSO (for adaptive lasso) or LASSO (for Lasso) penalty
crit	can be BIC, AIC or GCV, default is BIC
...

Value

class ProbitLasso containing penalized probit coefficients similar to the GLMNET package results. Linear predictor and fitted values are returned

Examples

ProbitLasso(formula, data=data, allowParallel = TRUE, penalty="ALASSO", crit="bic")

EOgundimu300/HeckmanSelect documentation built on Feb. 5, 2022, 2:48 a.m.