EMcvlasso: cross validation for 'EMlasso'
In HDPenReg: High-Dimensional Penalized Regression

Description Usage Arguments Value Author(s) Examples

cross validation function for EMlasso.

1
2
3

EMcvlasso(X, y, lambda = NULL, nbFolds = 10, maxSteps = 1000,
  intercept = TRUE, model = c("linear", "logistic"), burn = 30,
  threshold = 1e-08, eps = 1e-05, epsCG = 1e-08)

`X`	the matrix (of size n*p) of the covariates.
`y`	a vector of length n with the response.
`lambda`	Values at which prediction error should be computed.
`nbFolds`	the number of folds for the cross-validation.
`maxSteps`	Maximal number of steps for EM algorithm.
`intercept`	If TRUE, there is an intercept in the model.
`model`	"linear" or "logistic".
`burn`	Number of steps for the burn period.
`threshold`	Zero tolerance. Coefficients under this value are set to zero.
`eps`	Tolerance of the EM algorithm.
`epsCG`	Epsilon for the convergence of the conjugate gradient.

A list containing

cv: Mean prediction error for each value of index.
cvError: Standard error of lambda.
minCv: Minimal lambda criterion.
lambda: Values of lambda at which prediction error should be computed.
lambda.optimal: Value of lambda for which the cv criterion is minimal.

Quentin Grimonprez, Serge Iovleff

1
2
3

dataset <- simul(50, 100, 0.4, 1, 10, matrix(c(0.1,0.8,0.02,0.02),nrow=2))
result <- EMcvlasso(X = dataset$data, y = dataset$response,
                    lambda = 5:1, nbFolds = 5,intercept = FALSE)