Dspls
Purpose
Partial Least Squares computational engine using Direct Scores algorithm.
Synopsis
- [reg,ssq,xlds,ylds,wts,xscrs,yscrs,basis] = dspls(x,y,ncomp,options)
Please note that the recommended way to build a PLS model using the Direct Scores algorithm from the command line is to use the Model Object. Please see this wiki page on building models using the Model Object.
Description
Performs PLS regression using Direct Scores PLS algorithm as described in Andersson, "A comparison of nine PLS1 algorithms", J. Chemometrics, (www.interscience.wiley.com) DOI: 10.1002/cem.1248
This modified SIMPLS algorithm provides improved numerical stability for high numbers of latent variables.
Note: The regression matrices are ordered in reg such that each ny (number of Y-block variables) rows correspond to the regression matrix for that particular number of latent variables.
Inputs
- x = X-block (predictor block) class "double".
- y = Y-block (predicted block) class "double".
Optional Inputs
- ncomp = the number of latent variables to be calculated (positive integer scalar {default = rank of X-block}.
Outputs
- reg = matrix of regression vectors.
- ssq = the sum of squares captured.
- xlds = X-block loadings.
- ylds = Y-block loadings.
- wts = X-block weights, currently returns empty.
- xscrs = X-block scores.
- yscrs = Y-block scores, currently returns empty.
- basis = the basis of X-block loadings.
Options
options = a structure array with the following fields:
- display : [ 'off' |{'on'}] governs display to command window
- ranktest : [ 'none' | 'data' | 'scores' | {'auto'} ] governs type of rank test to perform.
- 'data' = single test on X-block (faster with smaller data blocks and more components).
- 'scores' = test during regression on scores matrix (faster with larger data matricies).
- 'auto' = auto selection, or 'none' = assume sufficient rank.