ade4 (version 1.01)

niche: Method to Analyse a pair of tables : Environmental and Faunistic Data

Description

performs a special multivariate analysis for ecological data.

Usage

niche(dudiX, Y, scannf = TRUE, nf = 2)
print.niche (x, ...) 
plot.niche (x, xax = 1, yax = 2, ...)

Arguments

dudiX

a duality diagram providing from a function dudi.coa, dudi.pca, ... using an array sites-variables

Y

a data frame sites-species according to dudiX$tab with no columns of zero

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

x

an object of class 'niche'

...

further arguments passed to or from other methods

xax, yax

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

Value

• Returns a list of the class 'niche' (sub-class of 'dudi') containing :
• rank
  an integer indicating the rank of the studied matrix
• nf
  an integer indicating the number of kept axes
• RV
  a numeric value indicating the RV coefficient
• eig
  a numeric vector with the all eigenvalues
• lw
  a data frame with the row weigths (crossed array)
• tab
  a data frame with the crossed array (averaging species/sites)
• li
  a data frame with the species coordinates
• l1
  a data frame with the species normed scores
• co
  a data frame with the variable coordinates
• c1
  a data frame with the variable normed scores
• ls
  a data frame with the site coordinates
• as
  a data frame with the axis upon niche axis

References

Dol�dec, S., Chessel, D. and Gimaret, C. (2000) Niche separation in community analysis: a new method. Ecology, 81, 2914--1927.

Examples

data(doubs)
dudi1 <- dudi.pca(doubs$mil, scale = TRUE, scan = FALSE, nf = 3)
nic1 <- niche(dudi1, doubs$poi, scann = FALSE)

par(mfrow = c(2,2))
s.traject(dudi1$li, clab = 0)
s.traject(nic1$ls, clab = 0)
s.corcircle(nic1$as)
s.arrow(nic1$c1)

par(mfrow = c(5,6))
for (i in 1:27) s.distri(nic1$ls, as.data.frame(doubs$poi[,i]),
    csub = 2, sub = names(doubs$poi)[i])

par(mfrow = c(1,1))
s.arrow(nic1$li, clab = 0.7)

par(mfrow = c(1,1))
data(trichometeo)
pca1 <- dudi.pca(trichometeo$meteo, scan = FALSE)
nic1 <- niche(pca1, log(trichometeo$fau + 1), scan = FALSE)
plot(nic1)

data(rpjdl)
plot(niche(dudi.pca(rpjdl$mil, scan = FALSE), rpjdl$fau, scan = FALSE))