koplsScale {kopls} | R Documentation |
Function for mean-centering and scaling of a matrix.
koplsScale(x, center = "mc", scale = "none")
x |
The matrix to be mean-centered and/or scaled. |
center |
Mean-centering type: Either 'mc' for column-wise mean-centering or 'no' for no mean-centering. |
scale |
Scaling type: 'uv' for scaling to unit variance, 'pareto' for Pareto scaling (sqrt(uv)) or 'no' for no scaling. |
A list with the following properties:
x |
The scaled matrix. |
meanVector |
Vector with mean values (possibly) used in the scaling. |
sdVector |
Vector with standard deviation values (possibly) used in the scaling. |
scale |
Scaling type: see link{koplsScale} for details. |
center |
Mean-centering type see link{koplsScale} for details. |
Max Bylesjo and Mattias Rantalainen
Rantalainen M, Bylesjo M, Cloarec O, Nicholson JK, Holmes E and Trygg J. Kernel-based orthogonal projections to latent structures (K-OPLS), J Chemometrics 2007; 21:376-385. doi:10.1002/cem.1071.