optional response type. Set automatically according to the
class type of the response variable.
alpha
elasticnet mixing parameter.
lambda
regularization parameter. The default value lambda = 0
performs no regularization and should be increased to avoid model fitting
issues if the number of predictor variables is greater than the number of
observations.
standardize
logical flag for predictor variable standardization, prior
to model fitting.
intercept
logical indicating whether to fit intercepts.
penalty.factor
vector of penalty factors to be applied to each
coefficient.
standardize.response
logical indicating whether to standardize
"mgaussian" response variables.
thresh
convergence threshold for coordinate descent.
maxit
maximum number of passes over the data for all lambda values.