search.desc.ktab {SensoMineR}R Documentation

Search for discriminating descriptors

Description

This function is designed to select the significant descriptors in an object of class ktab.

Usage

search.desc.ktab(ktab.donnee, level = 0.5)

Arguments

ktab.donnee an object of class ktab (i.e. a list of data frames with the same row.names in common)
level the threshold (P-value) below which variables are considered as discriminating for the analysis of variance model: descriptor=Panelist+Product

Details

The input data set is an object of class ktab for which the first element of the list (i.e. the first data frame) must correspond to a 2 qualitative variables block, where the first variable refers to the panelist variable and the second to the product variable.

Value

Returns an object of class ktab with only discriminating variables.

Author(s)

François Husson

Examples

data(chocolates)
#Construction of the ktab (J stands for Panelist and P stands for Product)
ktab.donnee <- ktab.data.frame(cbind.data.frame(chocolates[,1],
    chocolates[,4], chocolates[,5:ncol(chocolates)]), blocks = c(2,14), 
    tabnames = c("JP","Gr1"))
ktab.interesting.desc <- search.desc.ktab(ktab.donnee, level = 0.5)

[Package SensoMineR version 1.03 Index]