inertiaDistrib {FactoInvestigate}

Inertia distribution analysis

Description

Analysis of the inertia distribution among each axis, the amount and the significativity

Usage

inertiaDistrib(res, file = "", ncp = NULL, q = 0.95, time = "10000L", 
        parallel = TRUE, figure.title = "Figure", graph = TRUE, options = NULL)

Arguments

res

an object of class PCA, CA or MCA.

file

the file path where to write the description in Rmarkdown language. If not specified, the description is written in the console.

ncp

an integer to force the number of dimension to analyse.

q

the quantile of computed values to use as reference value (ie. the confidence about the signification of dimensions).

time

a character indicating the loop condition. This string is made of a number and a letter coupled. The number X with letter L means to compute X datasets exactly. The number X with letter s means to compute as many datasets as possible during approximativley X seconds.

parallel

a boolean : if TRUE, the computation uses map reduce on the processor cores to increase the performance. Useful for huge datasets.

figure.title

the text label to add before graph title.

graph

a boolean : if TRUE, graphs are plotted.

options

a character string that gives the output options fir the figures. If NULL, options="r, echo = FALSE, fig.align = 'center', fig.height = 3.5, fig.width = 5.5" for linux and Mac and options="r, echo = FALSE, fig.height = 3.5, fig.width = 5.5" for Windows

Value

ncp

the number of significant dimensions (or the dimensions kept).

Author(s)

Simon Thuleau and Francois Husson

See Also

dimRestrict, eigenRef

Examples

## Not run: 
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
inertiaDistrib(res.pca, q = 0.95, time = "10s")

data(children)
res.ca = CA(children, row.sup = 15:18, col.sup = 6:8, graph = FALSE)
inertiaDistrib(res.ca, q = 0.99, time = "10000L")

data(tea)
res.mca = MCA(tea, quanti.sup = 19,quali.sup = 20:36, graph = FALSE)
inertiaDistrib(res.mca, dim = 1:8, q = 0.90, time = "10s")

## End(Not run)