probe (version 1.1)

Sim_data: Simulated high-dimensional data set for sparse linear regression

Description

This dataset was simulated using a \(20 \times 20\) 2-dimensional setting described in the reference. The data contains 400 subjects with one outcome and 400 predictor variables. The test outcomes and predictor variables are contained in Sim_data_test.

Usage

data("Sim_data")

Format

A data frame with 400 observations and the following objects:

Y

Outcome variable of length \(400\).

X

A \(400 \times 400\) matrix of binary predictor variables.

signal

The locations of the non-zero regression coefficients.

beta_tr

The true values of all \(400\) regression coefficients.

sigma2_tr

The true value of the residual variance.

Examples

data(Sim_data)
attach(Sim_data)
length(Y)
dim(X)