powered by
It performs the lars algorithm for solving a special case of lasso problem. It is a linear regression problem with a l1-penalty on the difference of two successive coefficients.
HDfusion( X, y, maxSteps = 3 * min(dim(X)), intercept = TRUE, eps = .Machine$double.eps^0.5 )
An object of type LarsPath. LarsPath-class.
LarsPath
LarsPath-class
the matrix (of size n*p) of the covariates.
a vector of length n with the response.
Maximal number of steps for lars algorithm.
If TRUE, there is an intercept in the model.
Tolerance of the algorithm.
Quentin Grimonprez
Efron, Hastie, Johnstone and Tibshirani (2003) "Least Angle Regression" (with discussion) Annals of Statistics
LarsPath HDlars
set.seed(10) dataset <- simul(50, 10000, 0.4, 10, 50, matrix(c(0.1, 0.8, 0.02, 0.02), nrow = 2)) result <- HDfusion(dataset$data, dataset$response)
Run the code above in your browser using DataLab