extremal.index | R Documentation |
Estimates the extremal index of a time series.
extremal.index(x, threshold, silent = FALSE)
x |
Time series of class xts or numerical. |
threshold |
Only events exceeding a specific threshold will be considered extreme events and thus will be subject of the declustering. |
silent |
Whether or not to display warnings. |
The extremal index can be thought of as the inverse of the mean cluster size. It can be calculated by the blocks method of Ferro and Segers, 2003. I will use the bias-free estimator provided in equation (4) in their paper. This one is supposed to be the most robust one and is relying on a moment estimation.
Another way to estimate it, would be using the runs
method as in Stuart Coles (2001). But therefore one had to know
the minimal distance between the clusters first. Since the whole
point of this function to estimate exactly this quantity for its
use in the decluster
function, I don't see the
point of implementing this method too.
Numerical vector containing c( extremal index, number of clusters, minimal distance between clusters (minimal.distance))
Philipp Mueller
Other extremes: block.list
,
block.xts
, block
,
decluster.list
,
decluster.xts
, decluster
,
gev.density
, gpd.density
,
qevd
,
return.level.climex.fit.gev
,
return.level.climex.fit.gpd
,
return.level.list
,
return.level.numeric
,
return.level
, revd
,
rlevd
, threshold.list
,
threshold.xts
, threshold
,
upper.limit.climex.fit.gev
,
upper.limit.climex.fit.gpd
,
upper.limit.list
,
upper.limit.numeric
,
upper.limit
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.