atvnonpar(x = rep(1/3,3), data, nsloc1 = NULL, nsloc2 = NULL, nsloc3 = NULL,
method = c("pickands", "deheuvels", "hall"), plot = FALSE,
col = heat.colors(12), blty = 0, grid = if(blty) 150 else 50,
lower = 1/3, ord = 1:3, lab = as.character(1:3), lcex = 1)
TRUE
). The elements/rows
of the vector/matrix should be positive and should sum to onedata
, for linear modelling of the location
parameter on the first/second/third margin.
The data frames are treated as covariate matrices, excluding the
intercept.
A numeric vect"pickands"
(the default), "deheuvels"
or "hall"
(or any unique partial match). The three
estimators are very similar, and may not be distinguishabTRUE
the function is plotted. The
minimum (evaluated) value is returned invisibly.
If FALSE
(the default), the following arguments are
ignored.image
). The first
colours in the list represent smaller values, and hence
stronger dependence. Each colour represents an equally spaced
interval between lower
ablty
is zero, so no
border is plotted. Plotting a border leads to (by default) an
increase in grid
(and hence computation time), to grid^2
points.ord
.i
th margin is labelled using the i
th component,
or NULL
, in which case no labels are given. By default,
lab
is as.character(1:3)
lab
is NULL
.atvnonpar
calculates or plots a non-parametric estimate of
the dependence function of the trivariate extreme value distribution.atvpar
, abvnonpar
,
fgev
s3pts <- matrix(rexp(30), nrow = 10, ncol = 3)
s3pts <- s3pts/rowSums(s3pts)
sdat <- rmvevd(100, dep = 0.6, model = "log", d = 3)
atvnonpar(s3pts, sdat)
atvnonpar(data = sdat, plot = TRUE)
atvnonpar(data = sdat, plot = TRUE, ord = c(2,3,1), lab = LETTERS[1:3])
atvpar(dep = 0.6, model = "log", plot = TRUE)
atvpar(dep = 0.6, model = "log", plot = TRUE, blty = 1)
Run the code above in your browser using DataLab