choice.component.MB: choice.component

In martinparies/PCAOS: PCA.OS

choice.component

Description

Helps the user to choose the appropriate number of MBPCAOS component to optimize

Usage

choice.component.MB(
  data,
  level.scale,
  blocks,
  blocks.name,
  nb.comp.to.investigate = 5,
  block.scaling = "inertia",
  supp.var = NULL
)

Arguments

data	a data frame with n rows (individuals) and p columns (numeric, nominal and/or ordinal variables)
level.scale	vector(length p) giving the nature of each variable. Possible values: "nom", "ord", "num"
blocks	vector(length k) with number of variables in each bloc
blocks.name	vector(length k) with names of each bloc
nb.comp.to.investigate	Number of components to investigate (default=ncol(data))
block.scaling	scaling applied to each block. Possible value are : "inertia"(default): each quantified block is divided by its total inertia (sum of square). "lambda1" : each quantified block is divided by its the first singular value. "null" : no scaling is applied
supp.var	a vector indicating the indexes of the supplementary variables

Value

Data frame with global Loss value and percentage of the quantified variables inertia explained, for different model dimensionality (H). The last column provides the variation in percentage between to two successive size of dimensionality.

Author(s)

• Martin PARIES (Maintainer: [e-mail])

• Evelyne Vigneau

• Stephanie Bougeard

Examples

data('antibiotic')
antb.uses <- antibiotic[,c('Atb.conso','Atb.Sys')]
health <- antibiotic[,c('Age','Loss')]
vet.practices <- antibiotic[,c(6:15)]
antibiotic.MB <- data.frame(antb.uses,health,vet.practices)

# Defining the blocks
blocks.name =  c("antibiotic.uses","Health.of.turkeys","Veterinary.practices")
blocks <- c(2,2,10)

# Level of scaling
level.scale.MB <- rep(NA,ncol(antibiotic.MB))
res.nature <- nature.variables(antibiotic.MB)
level.scale.MB [res.nature$p.numeric] <- "num"
level.scale.MB [res.nature$p.quali] <- "nom"
#Warning; the ordinal nature of variables can not be detected automaticaly.
level.scale.MB[c(1,14)] <- "ord"

# Choice of number of components
help(choice.component.MB)
res.choice.MB <- choice.component.MB(antibiotic.MB,
                                     level.scale.MB,
                                     blocks,
                                     blocks.name,
                                     block.scaling = 'inertia')
res.choice.MB

martinparies/PCAOS documentation built on March 15, 2023, 7:19 a.m.