MFKnockoffs.create.gaussian: Sample multivariate Gaussian knockoff variables

Description Usage Arguments Value References See Also

Description

Samples multivariate Gaussian fixed-design knockoff variables for the original variables.

Usage

1
2
MFKnockoffs.create.gaussian(X, mu, Sigma, method = c("asdp", "sdp", "equi"),
  diag_s = NULL)

Arguments

X

normalized n-by-p realization of the design matrix

mu

mean vector of length p for X

Sigma

p-by-p covariance matrix for X

method

either 'equi', 'sdp' or 'asdp' (default:'asdp')

diag_s

pre-computed vector of covariances between the original variables and the knockoffs. This will be computed according to 'method', if not supplied

Value

n-by-p matrix of knockoff variables

References

Candes et al., Panning for Gold: Model-free Knockoffs for High-dimensional Controlled Variable Selection, arXiv:1610.02351 (2016). https://statweb.stanford.edu/~candes/MF_Knockoffs/index.html

See Also

Other methods for creating knockoffs: MFKnockoffs.create.approximate_gaussian, MFKnockoffs.create.fixed


MFKnockoffs documentation built on May 2, 2019, 6:33 a.m.