nsdr (version 0.1.1)

gram.gauss: gram.gauss

Description

gram.gauss

Usage

gram.gauss(x,x.new,complexity)

Arguments

x

previous observations

x.new

new observations

complexity

tuning parameter in Gaussian kernel

Value

Gram matrix for the Gaussian kernel. This also can be used to project predictor on the testing set.

References

Li, B. (2018). Sufficient dimension reduction: Methods and applications with R. CRC Press.

Examples

# NOT RUN {
old <- matrix(c(1,2,3,4),2,2)
new <- matrix(c(5,6,7,8),2,2)
result <- gram.gauss(old,new,1)
# }