noisyDonoho: Generate Donoho's Toy Data Sets

In CVST: Fast Cross-Validation via Sequential Testing

Generate Donoho's Toy Data Sets

Description

This function allows to generate noisy variants of the toy signals introduced by Donoho (see reference section). The scaling is chosen to reflect the setting as discussed in the original paper.

Usage

noisyDonoho(n, fun = doppler, sigma = 1)
blocks(x, scale = 3.656993)
bumps(x, scale = 10.52884)
doppler(x, scale = 24.22172)
heavisine(x, scale = 2.356934)

Arguments

n	Number of data points that should be generated.
fun	Function to use to generate the data.
sigma	Standard deviation of the noise component.
x	Number of data points that should be generated.
scale	Scaling parameter.

Value

Returns a data set of type CVST.data

Author(s)

Tammo Krueger <[e-mail]>

References

David L. Donoho and Jain M. Johnstone. Ideal spatial adaptation by wavelet shrinkage. Biometrika, 81 (3) 425–455, 1994.

See Also

constructData

Examples

bumpsSet = noisyDonoho(1000, fun=bumps)
plot(bumpsSet)
dopplerSet = noisyDonoho(1000, fun=doppler)
plot(dopplerSet)

CVST documentation built on March 18, 2022, 5:59 p.m.