cw.multiblock: Clusterwise multiblock analyses
In mbclusterwise: Clusterwise Multiblock Analyses

Description Usage Arguments Value Author(s) References See Also Examples

Function to perform a clusterwise multiblock analyses (clusterwise multiblock Partial Least Squares, clusterwise multiblock Redundancy Analysis or clusterwise regularized multiblock regression) of several explanatory blocks (X_1, …, X_K) to explain a dependent dataset Y.

1
2
3

cw.multiblock(Y, X, blo, option = c("none", "uniform"), G, H, INIT = 20, 
    method = c("mbpls", "mbpcaiv", "mbregular"), Gamma = NULL, 
    parallel.level = c("high", "low"))

`Y`	a matrix or data frame containing the dependent variable(s)
`X`	a matrix or data frame containing the explanatory variables
`blo`	a vector of the numbers of variables in each explanatory dataset
`option`	an option for the block weighting (by default, the first option is chosen): none the block weight is equal to the block inertia uniform the block weight is equal to 1/K for (X_1, …, X_K) and to 1 for X and Y
`G`	an integer giving the expected number of clusters
`H`	an integer giving the expected number of dimensions of the component-based model
`INIT`	an integer giving the number of initializations required for the clusterwise analysis (20 by default)
`method`	an option for the multiblock method to be applied (by default, the first option is chosen): mbpls multiblock Partial Least Squares is applied mbpcaiv multiblock Redundancy Analysis is applied mbregular multiblock regularized regression is applied
`Gamma`	a numeric value of the regularization parameter for the multiblock regularized regression comprised between 0 and 1 (NULL by default). The value (`Gamma=0`) leads to multiblock Redundancy Analysis and (`Gamma=1`) to multiblock PLS
`parallel.level`	Level of parallel computing, i.e. initializations are carried out simultaneously (high by default) high includes all the processing units of your computer low includes only two processing units of your computer

A list containing the following components is returned:

`call`	the matching call
`error`	a vector containing the value of the criterion to be minimized (overall prediction error) ; this error is performed on the centered and scaled data
`beta.cr`	a list of array that contain the intercept and the regression coefficients associated with the centered and scaled data for each of the G clusters
`beta.raw`	a list of array that contain the intercept and the regression coefficients associated with the raw data for each of the G clusters
`hopt`	the real number of dimensions of the component-based model (`hopt` is sometimes lower than the expected `H`)
`Ypred.cr`	a list of matrices that contain the predicted dependent values associated with the centered and scaled data for each of the G clusters
`Ypred.raw`	a list of matrices that contain the predicted dependent values associated with the raw data for each of the G clusters
`cluster`	a vector containing the observation assignation to the G expected clusters (when G>1 only)

Stephanie Bougeard (stephanie.bougeard@anses.fr)

Bougeard, S., Abdi, H., Saporta, G., Niang, N., Submitted, Clusterwise analysis for multiblock component methods.

cw.tenfold, cw.predict

  data(simdata.red) 
  Data.X <- simdata.red[c(1:10, 21:30), 1:10]
  Data.Y <- simdata.red[c(1:10, 21:30), 11:13]
  ## Note that the options (INIT=2) and (parallel.level = "low") are chosen to quickly
  ## illustrate the function. 
  ## For real data, instead choose (INIT=20) to avoid local optima and (parallel.level = "high")
  ## to improve the computing speed.
  res.cw <- cw.multiblock(Y = Data.Y, X = Data.X, blo = c(5, 5), option = "none", G = 2, 
            H = 1, INIT = 2, method = "mbpcaiv", Gamma = NULL, parallel.level = "low")