cv.glmnet.constr: CV for constrained lasso.

In stephenbates19/logratiolasso: Tools For Large Log Ratio Models

Description

Cross-validation to choose lambda in the constrained lasso procedure

Usage

cv.glmnet.constr(fit, x, y, nfolds = 10, foldid = NULL, keep = F,
  alpha = 1)

Arguments

fit	The result of a "glmnet.contsr" function call.
x	The matrix of features.
y	The response value. In the real-valued repsonse case, y should be centered.
nfolds	The number of CV folds. Default is 10.
foldid	Fold id for each observation. By default these are uniformly random.
alpha	Elastic net parameter. Default is 1 which gives the lasso.

Value

lambda The gride of lambda values

cvm The CV estimate of prediction error for each lambda.

yhat.preval The predicted values generated by each fold.

stephenbates19/logratiolasso documentation built on May 18, 2019, 4:52 p.m.