screen_trex {TRexSelector}

Run the Screen-T-Rex selector (doi:10.1109/SSP53291.2023.10207957)

Description

The Screen-T-Rex selector (doi:10.1109/SSP53291.2023.10207957) performs very fast variable selection in high-dimensional settings while informing the user about the automatically selected false discovery rate (FDR).

Usage

screen_trex(
  X,
  y,
  K = 20,
  R = 1000,
  method = "trex",
  bootstrap = FALSE,
  conf_level_grid = seq(0, 1, by = 0.001),
  cor_coef = NA,
  type = "lar",
  corr_max = 0.5,
  lambda_2_lars = NULL,
  rho_thr_DA = 0.02,
  parallel_process = FALSE,
  parallel_max_cores = min(K, max(1, parallel::detectCores(logical = FALSE))),
  seed = NULL,
  eps = .Machine$double.eps,
  verbose = TRUE
)

Arguments

X

Real valued predictor matrix.

y

Response vector.

K

Number of random experiments.

R

Number of bootstrap resamples.

method

'trex' for the T-Rex selector (doi:10.48550/arXiv.2110.06048), 'trex+GVS' for the T-Rex+GVS selector (doi:10.23919/EUSIPCO55093.2022.9909883), 'trex+DA+AR1' for the T-Rex+DA+AR1 selector, 'trex+DA+equi' for the T-Rex+DA+equi selector.

bootstrap

Logical. If TRUE Screen-T-Rex is carried out with bootstrapping.

conf_level_grid

Confidence level grid for the bootstrap confidence intervals.

cor_coef

AR(1) autocorrelation coefficient for the T-Rex+DA+AR1 selector or equicorrelation coefficient for the T-Rex+DA+equi selector.

type

'lar' for 'LARS' and 'lasso' for Lasso.

corr_max

Maximum allowed correlation between any two predictors from different clusters.

lambda_2_lars

lambda_2-value for LARS-based Elastic Net.

rho_thr_DA

Correlation threshold for the T-Rex+DA+AR1 selector and the T-Rex+DA+equi selector (i.e., method = 'trex+DA+AR1' or 'trex+DA+equi').

parallel_process

Logical. If TRUE random experiments are executed in parallel.

parallel_max_cores

Maximum number of cores to be used for parallel processing.

seed

Seed for random number generator (ignored if parallel_process = FALSE).

eps

Numerical zero.

verbose

Logical. If TRUE progress in computations is shown.

Value

A list containing the estimated support vector, the automatically selected false discovery rate (FDR) and additional information.

Examples

data("Gauss_data")
X <- Gauss_data$X
y <- c(Gauss_data$y)
set.seed(123)
res <- screen_trex(X = X, y = y)
selected_var <- res$selected_var
selected_var