ade4 (version 1.7-5)

statis: STATIS, a method for analysing K-tables

Description

performs a STATIS analysis of a ktab object.

Usage

statis(X, scannf = TRUE, nf = 3, tol = 1e-07)
"plot"(x, xax = 1, yax = 2, option = 1:4, ...) 
"print"(x, ...)

Arguments

X

an object of class 'ktab'

scannf

a logical value indicating whether the number of kept axes for the compromise should be asked

nf

if scannf FALSE, an integer indicating the number of kept axes for the compromise

tol

a tolerance threshold to test whether the distance matrix is Euclidean : an eigenvalue is considered positive if it is larger than -tol*lambda1 where lambda1 is the largest eigenvalue

x

an object of class 'statis'

xax, yax

the numbers of the x-axis and the y-axis

option

an integer between 1 and 4, otherwise the 4 components of the plot are dispayed

...

further arguments passed to or from other methods

Value

statis returns a list of class 'statis' containing :

References

Lavit, C. (1988) Analyse conjointe de tableaux quantitatifs, Masson, Paris. Lavit, C., Escoufier, Y., Sabatier, R. and Traissac, P. (1994) The ACT (Statis method). Computational Statistics and Data Analysis, 18, 97--119.

Examples

data(jv73)
kta1 <- ktab.within(withinpca(jv73$morpho, jv73$fac.riv, scann = FALSE))
statis1 <- statis(kta1, scann = FALSE)
plot(statis1)

dudi1 <- dudi.pca(jv73$poi, scann = FALSE, scal = FALSE)
wit1 <- wca(dudi1, jv73$fac.riv, scann = FALSE)
kta3 <- ktab.within(wit1)
data(jv73)
statis3 <- statis(kta3, scann = FALSE)
plot(statis3)

if(adegraphicsLoaded()) {
  s.arrow(statis3$C.li, pgrid.text.cex = 0)
  kplot(statis3, traj = TRUE, arrow = FALSE, plab.cex = 0, psub.cex = 3, ppoi.cex = 3)
} else {
  s.arrow(statis3$C.li, cgrid = 0)
  kplot(statis3, traj = TRUE, arrow = FALSE, unique = TRUE, 
    clab = 0, csub = 3, cpoi = 3)
}

statis3