Ncrossval: Difference between revisions

Latest revision as of 13:42, 10 August 2010

Redirect to:

@@ Line 1: / Line 1: @@
-===Purpose===
+#REDIRECT [[crossval]]
-Cross-validation for multilinear PLS (NPLS).
-===Synopsis===
-:[press,cumpress,rmsecv,rmsec,cvpred,misclassed] = ncrossval(x,y,rm,cvi,ncomp,out,pre)
-===Description===
-Performs cross-validation of NPLS. If two-way unfold-PLS is desired convert input x to two-way x. By default, the data are centered across the first mode, but no scaling is applied. This can be changed by using additional input arguments.
-INPUTS:
-* x = X-block matrix,
-* y = Y-block matrix, and
-*                      rm  = regression method (must be 'npl')
-*           cvi = see CROSSVAL
-* ncomp = maximum number of factors.
-*    out = see CROSSVAL
-*    pre = see CROSSVAL
-OUTPUT:
-* See CROSSVAL
-===See Also===
-[[crossval]], [[npls]]