pcaLR: generates a closure for the computation of the likelihood...

In kernelPSI: Post-Selection Inference for Nonlinear Variable Selection

Description

This function implements the same prototype statistics in the ridgeLR function, but for kernel principal component regression (see reference). In our simulations, we observed that this method underperforms the ridge prototype. The main benefit of this approach is the possibility of exact post-selection without the need for replicates sampling.

Usage

pcaLR(K, mu = 0, sigma = 1)

Arguments

K	a single or a list of selected kernel similarity matrices.
mu	marginal mean of the response Y
sigma	standard deviation of the response

Value

a closure for the calculation of the LR statistic for the kernel PCA prototype

References

Rosipal, R., Girolami, M., Trejo, L. J., & Cichocki, A. (2001). Kernel PCA for feature extraction and de-noising in nonlinear regression. Neural Computing and Applications, 10(3), 231–243.

See Also

Other prototype: ridgeLR()

Examples

n <- 30
p <- 20
K <- replicate(5, matrix(rnorm(n*p), nrow = n, ncol = p), simplify = FALSE)
K <-  sapply(K, function(X) return(X %*% t(X) / dim(X)[2]), simplify = FALSE)
print(typeof(pcaLR(K, mu = 0, sigma = 1)) == "closure")

kernelPSI documentation built on Dec. 8, 2019, 1:07 a.m.