lasso_perm {adapt4pv}R Documentation

fit a lasso regression and use standard permutation of the outcome for variable selection


Performed K lasso logistic regression with K different permuted version of the outcome. For earch of the lasso regression, the λ_max(i.e. the smaller λ such as all penalized regression coefficients are shrunk to zero) is obtained. The median value of these K λ_max is used to for variable selection in the lasso regression with the non-permuted outcome. Depends on the glmnet function from the package glmnet.


lasso_perm(x, y, K = 20, keep = NULL, betaPos = TRUE, ncore = 1, ...)



Input matrix, of dimension nobs x nvars. Each row is an observation vector. Can be in sparse matrix format (inherit from class "sparseMatrix" as in package Matrix).


Binary response variable, numeric.


Number of permutations of y. Default is 20.


Do some variables of x have to be permuted in the same way as y? Default is NULL, means no. If yes, must be a vector of covariates indices. TEST OPTION


Should the covariates selected by the procedure be positively associated with the outcome ? Default is TRUE.


The number of calcul units used for parallel computing. Default is 1, no parallelization is implemented.


Other arguments that can be passed to glmnet from package glmnet other than family.


The selected λ with this approach is defined as the closest λ from the median value of the K λ_max obtained with permutation of the outcome.


An object with S3 class "log.lasso".


Numeric vector of regression coefficients in the lasso In lasso_perm function, the regression coefficients are PENALIZED. Length equal to nvars.


Character vector, names of variable(s) selected with the lasso-perm approach. If betaPos = TRUE, this set is the covariates with a positive regression coefficient in beta. Else this set is the covariates with a non null regression coefficient in beta. Covariates are ordering according to magnitude of their regression coefficients absolute value.


Emeline Courtois
Maintainer: Emeline Courtois


Sabourin, J. A., Valdar, W., & Nobel, A. B. (2015). "A permutation approach for selecting the penalty parameter in penalized model selection". Biometrics. 71(4), 1185–1194, doi: 10.1111/biom.12359


drugs <- matrix(rbinom(100*20, 1, 0.2), nrow = 100, ncol = 20)
colnames(drugs) <- paste0("drugs",1:ncol(drugs))
ae <- rbinom(100, 1, 0.3)
lp <- lasso_perm(x = drugs, y = ae, K = 10)

[Package adapt4pv version 0.2-1 Index]