ade4 (version 1.7-19)

mcoa: Multiple CO-inertia Analysis

Description

performs a multiple CO-inertia analysis, using an object of class ktab.

Usage

mcoa(X, option = c("inertia", "lambda1", "uniform", "internal"), 
    scannf = TRUE, nf = 3, tol = 1e-07)
# S3 method for mcoa
print(x, ...)
# S3 method for mcoa
summary(object, ...)
# S3 method for mcoa
plot(x, xax = 1, yax = 2, eig.bottom = TRUE, ...)

Value

mcoa returns a list of class 'mcoa' containing :

pseudoeig

a numeric vector with the all pseudo eigenvalues

call

the call-up order

nf

a numeric value indicating the number of kept axes

SynVar

a data frame with the synthetic scores

axis

a data frame with the co-inertia axes

Tli

a data frame with the co-inertia coordinates

Tl1

a data frame with the co-inertia normed scores

Tax

a data frame with the inertia axes onto co-inertia axis

Tco

a data frame with the column coordinates onto synthetic scores

TL

a data frame with the factors for Tli Tl1

TC

a data frame with the factors for Tco

T4

a data frame with the factors for Tax

lambda

a data frame with the all eigenvalues (computed on the separate analyses)

cov2

a numeric vector with the all pseudo eigenvalues (synthetic analysis)

Arguments

X

an object of class ktab

option

a string of characters for the weightings of the arrays options :

"inertia"

weighting of group k by the inverse of the total inertia of the array k

"lambda1"

weighting of group k by the inverse of the first eigenvalue of the k analysis

"uniform"

uniform weighting of groups

"internal"

weighting included in X$tabw

scannf

a logical value indicating whether the eigenvalues bar plot should be displayed

nf

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

tol

a tolerance threshold, an eigenvalue is considered positive if it is larger than -tol*lambda1 where lambda1 is the largest eigenvalue.

x, object

an object of class 'mcoa'

...

further arguments passed to or from other methods

xax, yax

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

eig.bottom

a logical value indicating whether the eigenvalues bar plot should be added

Author

Daniel Chessel
Anne-Béatrice Dufour

References

Chessel, D. and Hanafi, M. (1996) Analyses de la co-inertie de K nuages de points, Revue de Statistique Appliquée, 44, 35--60.

Examples

data(friday87)
w1 <- data.frame(scale(friday87$fau, scal = FALSE))
w2 <- ktab.data.frame(w1, friday87$fau.blo, tabnames = friday87$tab.names)
mcoa1 <- mcoa(w2, "lambda1", scan = FALSE)
mcoa1
summary(mcoa1)
plot(mcoa1)