| boot.matrix {extRemes} | R Documentation |
Set up matrices for bootstrapping sequences of extreme values.
boot.matrix(x, y)
x |
Output from decluster.runs or decluster.intervals. |
y |
Vector of observations. |
This function merely formats the information needed by boot.sequence to improve efficiency.
A list containing two (unamed) matrices, each with columns corresponding to clusters identified in 'x.'
comp1 |
inter-exceedance times |
comp2 |
Data values in 'y' corresponding to the exceedances in each cluster. |
Maintained by Eric Gilleland.
Chris Ferro
boot.sequence, decluster.intervals, decluster.runs
# Simulate 1000 uniform random variables.
x <- runif(1000)
# Perform runs declustering with run length = 1 and 90th percentile as threshold.
u <- quantile(x, 0.9)
z <- x > u
dec <- decluster.runs(z, 1)
# Make sure estimated run length is not zero before doing the rest.
if( dec[["par"]] != 0) {
# Set up the matrices for bootstrapping.
mat <- boot.matrix(dec, x)
# Bootstrap with 500 iterations.
eib <- numeric(500)
for( i in 1:500) {
set.seed(i)
zb <- boot.sequence(mat[[1]],mat[[2]],u) > u
eib[i] <- exi.intervals(zb)
} # end of for 'i' loop.
# Obtain bootstrapped 95th percentile confidence intervals.
conf.int <- quantile( eib, c((1-0.95)/2,(1+0.95)/2))
} # end of if run length estimate not zero stmt.