Component of the distance to build a stationary kernel function or similar.
$$M=\sum {w_i*(x'_i-x_i^{T})}^{power}$$
where \(x_i\) is the \(i^{th}\) column of the input matrix; \(w_i\) is the \(i^{th}\) element of the weight vector. Note that \(x\) and \(x'\) might be different.
xixj_sta(mat,mat.new=NULL,w=NULL,power=NULL)Input data, could be a matrix or a vector.
Second input data, could be a vector or a matrix. Default to be NULL. If NULL, mat.new=mat.
Weight to be add on each column of the matrix.
Argument 'power' X 2 will be the power to put on the distance. Default power is 1, which means \(distance^2\). The range of the power to put on the distance is 0 to 2, thus argument 'power' is from 0 to 1.
A symmetric matrix used to build the linear kernel or similar
If one wants to involve stationary kernel components in customized covariance matrix, this function will be used in derivatives of the kernel function. See examples in demo('co2').
Shi, J Q., and Choi, T. (2011), Gaussian Process Regression Analysis for Functional Data, Springer, New York.