mgc (version 2.0.2)

mgc.sims.spiral: Spiral Simulation

Description

A function for Generating a spiral simulation.

Usage

mgc.sims.spiral(n, d, eps = 0.4, a = 0, b = 5)

Arguments

n

the number of samples for the simulation.

d

the number of dimensions for the simulation setting.

eps

the noise level for the simulation. Defaults to 0.5.

a

the lower limit for the data matrix. Defaults -1.

b

the upper limit for the data matrix. Defaults to 1.

Value

a list containing the following:

X

[n, d] the data matrix with n samples in d dimensions.

Y

[n] the response array.

Details

Given: \(U \sim U(a, b)\) a random variable. Simumlates \(n\) points from \(Spiral(X, Y) \in \mathbf{R}^d \times \mathbf{R}\) where: \(X_i = U\, \textrm{cos}(\pi\, U)^d\) if i = d, and \(U\, \textrm{sin}(\pi U)\textrm{cos}^i(\pi U)\) otherwise $$Y = U\, \textrm{sin}(\pi\, U) + \epsilon p N(0, 1)$$

For more details see the help vignette: vignette("sims", package = "mgc")

Examples

# NOT RUN {
library(mgc)
result  <- mgc.sims.spiral(n=100, d=10)  # simulate 100 samples in 10 dimensions
X <- result$X; Y <- result$Y
# }