eisera {adehabitat} | R Documentation |
Performs an eigenanalysis of selection ratios.
eisera(used, available, scannf = TRUE, nf = 2) ## S3 method for class 'esr': print(x, ...) ## S3 method for class 'esr': scatter(x, xax = 1, yax = 2, csub = 1, possub = "bottomleft", ...)
used |
a data frame containing the *number* of relocations of each animal (rows) in each habitat type (columns) |
available |
a data frame containing the *proportion* of availability of each habitat type (columns) to each animal (rows) |
scannf |
logical. 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 esr |
xax |
the column number for the x-axis |
yax |
the column number for the y-axis |
csub |
a character size for the legend, used with
par("cex")*csub |
possub |
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft", "bottomright") |
... |
further arguments passed to or from other methods |
The eigenanalysis of selection ratios has been developped to explore
habitat selection by animals monitored using radio-tracking, when
habitat is defined by several categories (e.g. several vegetation
types, see Calenge and Dufour 2006).
This analysis can be used for both designs II (same availability for all animals, e.g. selection of the home range within the study area) and designs III (different availability, e.g. selection of the sites within the home range). In the latter case, when some available proportions are equal to zero, the selection ratios are replaced by their expectation under random habitat use, following the recommendations of Calenge and Dufour (2006).
A list of class esr
and dudi
containing also:
available |
available proportions |
used |
number of relocations |
wij |
selection ratios |
Clement Calenge clement.calenge@oncfs.gouv.fr
Calenge, C. and Dufour, A.B. (2006) Eigenanalysis of selection ratios from animal radio-tracking data. Ecology. 87, 2349–2355.
wi
for further information about the
selection ratios, compana
for compositional analysis.
########################################################### ########################################################### ### ### Example given in Calenge and Dufour 2006 (design II) data(squirrel) ## computation of the number of relocations in each habitat type ## from the data given by Aebischer et al. (1993). ## squirrel$locs give the percentage of relocations in each habitat ## type, and Aebischer et al. (1993) indicate that there are 30 ## relocations per animal. ## We therefore compute the number of relocations in each habitat type ## using: us <- round(30 * squirrel$locs / 100) ## Habitat availability av <- squirrel$studyarea ## Eigenanalysis of selection ratios ii <- eisera(us, av, scannf = FALSE) scatter(ii, grid = FALSE, clab = 0.7) ## The following graph may help the interpretation ## (see Calenge and Dufour 2006) data(squirreloc) locs <- squirreloc$locs are <- squirreloc$map co <- attr(are, "info") li <- split(locs[,2:3], locs[,1]) opar <- par(mfrow=n2mfrow(length(li)), mar=c(0,0,2,0)) lapply(1:length(li), function(i) { plot(are, colp = co[,2], main=names(li)[i], axes=FALSE) points(li[[i]], pch=16, cex=1.5) box() }) plot(0,0, axes=FALSE, ty="n", xlim=c(-1,1), asp=1) legend(-0.8,0.8, unique(co[,1]), fill=unique(co[,2])) par(opar) ########################################################### ########################################################### ### ### Example of design III iii <- eisera(us, squirrel$mcp, scannf = FALSE) scatter(iii, grid = FALSE, clab = 0.7)