Constructor method for fitting a T-PLS model with given data X and Y.
TPLS(X, Y, NComp = 25, W = NULL, nmc = 0)Numerical matrix of predictors. Typically single-trial betas where each column is a voxel and row is observation
Variable to predict. Binary 0 and 1 in case of classification, continuous variable in case of regression
(Optional) Number of PLS components to compute. Default is 25.
(Optional) Observation weights. By default, all observations have equal weight.
(Optional) 'no mean centering'. Default is 0. If 1, T-PLS will skip mean-centering. This option is only provided in case you already mean-centered the data and want to save some memory usage.
A TPLS object that contains the following attributes. Most of the time, you won't need to access the attributes.
NComp: The number of components you specified in the input
W: Normalized version of the observation weights (i.e., they sum to 1)
MtrainX: Column mean of X. Weighted mean if W is given.
MtrainY: Mean of Y. Weighted mean if W is given.
scoreCorr: Correlation between Y and each PLS component. Weighted correlation if W is given.
pctVar: Proportion of variance of Y that each component explains.
betamap: v-by-NComp matrix of TPLS coefficients for each of the v variables, provided at each model with NComp components.
threshmap : v-by-NComp matrix of TPLS threshold values (0~1) for each of the v variables, provided at each model with NComp components.
See vignettes for tutorial