| Title: | RcppEigen back end for sparse least trimmed squares regression |
|---|---|
| Description: | Use RcppEigen to fit least trimmed squares regression models with an L1 penalty in order to obtain sparse models. |
| Authors: | Andreas Alfons [aut, cre] |
| Maintainer: | Andreas Alfons <[email protected]> |
| License: | GPL (>= 2) |
| Version: | 0.2.0.1 |
| Built: | 2024-11-05 06:35:21 UTC |
| Source: | CRAN |
Use RcppEigen to fit least trimmed squares regression models with an L1 penalty in order to obtain sparse models.
| Package: | sparseLTSEigen |
| Type: | Package |
| Version: | 0.2.0 |
| Date: | 2013-11-13 |
| Depends: | robustHD (>= 0.4.0) |
| Imports: | Rcpp (>= 0.9.10), RcppEigen (>= 0.2.0) |
| Suggests: | mvtnorm |
| LinkingTo: | Rcpp, RcppEigen |
| License: | GPL (>= 2) |
| LazyLoad: | yes |
Index:
sparseLTSEigen-package
RcppEigen back end for sparse least trimmed
squares regression
Package sparseLTSEigen provides an alternative back end for sparse least trimmed squares regression from package robustHD. The back end built into robustHD uses the C++ library Armadillo, whereas this back end uses the C++ library Eigen. The latter is faster, but currently does not work on 32-bit R for Windows.
When sparseLTSEigen is loaded, its back end is used automatically for sparse least trimmed squares regression, except on 32-bit R for Windows.
Andreas Alfons [aut, cre]
Maintainer: Andreas Alfons <[email protected]>
# example is not high-dimensional to keep computation time low library("mvtnorm") set.seed(1234) # for reproducibility n <- 100 # number of observations p <- 25 # number of variables beta <- rep.int(c(1, 0), c(5, p-5)) # coefficients sigma <- 0.5 # controls signal-to-noise ratio epsilon <- 0.1 # contamination level Sigma <- 0.5^t(sapply(1:p, function(i, j) abs(i-j), 1:p)) x <- rmvnorm(n, sigma=Sigma) # predictor matrix e <- rnorm(n) # error terms i <- 1:ceiling(epsilon*n) # observations to be contaminated e[i] <- e[i] + 5 # vertical outliers y <- c(x %*% beta + sigma * e) # response x[i,] <- x[i,] + 5 # bad leverage points ## fit sparse LTS model # since package sparseLTSEigen is loaded, its back end based on # the C++ library Eigen is used rather than the back end built # into package robustHD, except on 32-bit R for Windows fit <- sparseLTS(x, y, lambda = 0.05, mode = "fraction") coef(fit, zeros = FALSE)# example is not high-dimensional to keep computation time low library("mvtnorm") set.seed(1234) # for reproducibility n <- 100 # number of observations p <- 25 # number of variables beta <- rep.int(c(1, 0), c(5, p-5)) # coefficients sigma <- 0.5 # controls signal-to-noise ratio epsilon <- 0.1 # contamination level Sigma <- 0.5^t(sapply(1:p, function(i, j) abs(i-j), 1:p)) x <- rmvnorm(n, sigma=Sigma) # predictor matrix e <- rnorm(n) # error terms i <- 1:ceiling(epsilon*n) # observations to be contaminated e[i] <- e[i] + 5 # vertical outliers y <- c(x %*% beta + sigma * e) # response x[i,] <- x[i,] + 5 # bad leverage points ## fit sparse LTS model # since package sparseLTSEigen is loaded, its back end based on # the C++ library Eigen is used rather than the back end built # into package robustHD, except on 32-bit R for Windows fit <- sparseLTS(x, y, lambda = 0.05, mode = "fraction") coef(fit, zeros = FALSE)