lasso and ridge regression

Previous Topic Next Topic
classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view

lasso and ridge regression

Gafar Matanmi Oyeyemi
Dear All

The problem is about regularization methods in multiple regression when the
independent variables are collinear. A modified regularization method with
two tuning parameters l1 and l2 and their product l1*l2 (Lambda 1 and
Lambda 2) such that l1 takes care of ridge property and l2 takes care of
LASSO property is proposed

The proposed method is given

The problem is how to adapt "glmnet" to accomplish our task.

The extract of the code used is reproduced as follows;

    cv.ridge<- glmnet(x, y, family="gaussian", alpha=0,
    lambda=lambda1, standardize=TRUE)
    cv.lasso<- glmnet(x, y, family="gaussian", alpha=1,
    lambda=lambda2, standardize=TRUE)
    a=1/abs(matrix(coef(cv.ridge, s=lambda1)[, 1][2:(ncol(x)+1)]
    b=1/abs(matrix(coef(cv.lasso, s=lambda2)[, 1][2:(ncol(x)+1)]
    w4 <-a+b+c
    w4[w4[,1] == Inf] <- 9
    # Fit modified procedure
    fit<- glmnet(x, y, family="gaussian",
    alpha=alpha,lambda=lambda1+lambda2, penalty.factor=w4)

The question is; Does the code address the modified procedure in as shown
in the equation? If not, suggestions are please welcome.


OYEYEMI, Gafar Matanmi (Ph.D)
Department of Statistics
University of Ilorin.
Area of Specialization: Multivariate Analysis, Statistical Quality Control
& Total Quality Management.
Tel: +2348052278655, +2348068241885

        [[alternative HTML version deleted]]

[hidden email] mailing list -- To UNSUBSCRIBE and more, see
PLEASE do read the posting guide
and provide commented, minimal, self-contained, reproducible code.