mbregular: Regularized multiblock regression
In mbclusterwise: Clusterwise Multiblock Analyses

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

Function to perform the regularized multiblock regression which gives results comprised the ones from multiblock Redundancy Analysis (gamma=0) and multiblock PLS (gamma=1). This method is applied to several explanatory blocks (X_1, …, X_K) defined as an object of class ktab (from ade4), to explain a dependent dataset Y defined as an object of class dudi (from ade4).

1	mbregular(dudiY, ktabX, scale = FALSE, option = c("none", "uniform"), H, gamma)

`dudiY`	an object of class `dudi` (from `ade4`) containing the dependent variable(s)
`ktabX`	an object of class `ktab` (from `ade4`) containing the blocks of explanatory variables
`scale`	a logical value indicating whether the explanatory variables should be standardized
`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
`H`	an integer giving the number of dimensions
`gamma`	a numeric value of the regularization parameter comprised between 0 and 1. The value (`gamma=0`) leads to multiblock Redundancy Analysis and (`gamma=1`) to multiblock PLS

A list containing the following components is returned:

`crit.reg`	the regression error
`lX`	a matrix of the global components associated with the whole explanatory dataset (scores of the individuals)
`XYcoef`	a list of matrices of the regression coefficients of the whole explanatory dataset onto the dependent dataset
`intercept`	a list of matrices of the regression intercepts of the whole explanatory dataset onto the dependent dataset
`fitted`	a list of matrices which contain the predicted dependent values

Stephanie Bougeard (stephanie.bougeard@anses.fr)

Bougeard, S., Qannari, E.M., Lupo, C. and Hanafi, M. (2011). From multiblock partial least squares to multiblock redundancy analysis. A continuum approach. Informatica, 22(1), 11-26

cw.multiblock, cw.tenfold, cw.predict, mbpcaiv, mbpls

  data(simdata.red) 
  Data.X <- simdata.red[c(1:15, 21:35), 1:10]
  Data.Y <- simdata.red[c(1:15, 21:35), 11:13]
  library(ade4)
  dudiy  <- dudi.pca(df = Data.Y, center = FALSE, scale = FALSE, scannf = FALSE)
  ktabx  <- ktab.data.frame(df = data.frame(Data.X), blocks = c(5,5), 
   tabnames = paste("Tab", c(1:2), sep = "."))
  res    <- mbregular(dudiy, ktabx, scale = FALSE, option = "none", H = 2, gamma = 0.8)