gen.data: Data Generation

In Kaiyuan-Carl-Duan/R-package-AutoLasso:

Description

Generate a random n by n*ratio matrix with the scale of beta in (-1,1). The number of active variables is p.true. User can input the correlation of data rho and signal to noise ratio. Also change the two different correlation generate methods.

Usage

gen.data(n=100,ratio=0.5,p.true=5,rho=0,cor.type=1,snr=10)

Arguments

n	Number of rows of generated data
ratio	Ratio is the proportion of the number of columns over that of the rows.
p.true	Number of active variables
rho	Correlation generate methods
cor.type	Different type of Sigma: Auto regressive(1), Compound symmetry(2)
snr	Signal to noise ratio

Details

n=100,ratio=0.5,p.true=5,rho=0,cor.type=1,snr=10

Value

A list contains three matrices: response variables, predicted variables, beta true and one scalar sigma true.

Author(s)

Sujit K. Ghosh, Kaiyuan Duan, Guangjie Yu

References

A Fast Automatic Variable Selection Method for LinearRegression Model

Examples

mydata=gen.data(n=100,ratio=0.1,rho=0.25)

Kaiyuan-Carl-Duan/R-package-AutoLasso documentation built on Dec. 18, 2021, 2:40 a.m.