Usage
correg(X = X, Y = Y, Z = NULL, B = NULL, compl = TRUE, expl = FALSE,
explnew = FALSE, pred = FALSE, prednew = FALSE, select = "lar",
criterion = c("MSE", "BIC"), X_test = NULL, Y_test = NULL,
intercept = TRUE, K = 10, groupe = NULL, Amax = NULL, lambda = 1,
returning = FALSE, final = FALSE, nbalter = 10, deltamin = 0.01,
alpha = NULL, g = 5)Arguments
X
the data matrix (covariates) without the intercept
Y
The response variable vector
Z
The structure (adjacency matrix) between the covariates
B
the (p+1)xp matrix associated to Z and that contains the parameters of the sub-regressions
compl
boolean to decide if the complete modele is computed
expl
boolean to decide if the explicative model is in the output
explnew
select the number of sub-regression to take into account (by AIC on the corresponding final model)
pred
boolean to decide if the predictive model is computed
prednew
alternate optimisation for predictive
select
selection method in ("lar","lasso","forward.stagewise","stepwise", "elasticnet", "NULL","ridge","adalasso","clere","spikeslab")
criterion
the criterion used to compare the models
Y_test
response for the validation sample
intercept
boolean. If FALSE intercept will be set to 0 in each model.
K
the number of clusters for cross-validation
groupe
a vector to define the groups used for cross-validation (to obtain a reproductible result)
Amax
the maximum number of covariates in the final model
lambda
parameter for elasticnet (quadratic penalty)
returning
boolean : second predictive step (selection on I1 knowing I2 coefficients)
final
boolean : recompute estimators without selection on the remaining parameters of the predictive model
nbalter
number of alternance for prednew
deltamin
criterion to stop alternance
alpha
Coefficients of the explicative model to coerce the predictive step. if not NULL explicative step is not computed.
g
number of group of variables for clere