gppiece {longevity} | R Documentation |
Piece-wise generalized Pareto distribution
Description
Density, distribution, quantile functions and random number generation from the
mixture model of Northrop and Coleman (2014), which consists of m
different generalized Pareto distributions over non-overlapping intervals
with m
shape parameters and one scale parameter; the other scale parameters are
constrained so that the resulting distribution is continuous over the domain
and reduces to a generalized Pareto distribution if all of the shape parameters are equal.
Usage
dgppiece(x, scale, shape, thresh, log = FALSE)
pgppiece(q, scale, shape, thresh, lower.tail = TRUE, log.p = FALSE)
qgppiece(p, scale, shape, thresh, lower.tail = TRUE, log.p = FALSE)
rgppiece(n, scale, shape, thresh)
Arguments
x , q |
vector of quantiles |
scale |
positive value for the first scale parameter |
shape |
vector of |
thresh |
vector of |
log , log.p |
logical; if |
lower.tail |
logical; if TRUE (default), probabilities are |
p |
vector of probabilities |
n |
sample size |
Value
a vector of quantiles (qgppiece
), probabilities (pgppiece
), density (dgppiece
) or random number generated from the model (rgppiece
)
References
Northrop & Coleman (2014). Improved threshold diagnostic plots for extreme value analyses, Extremes, 17(2), 289–303.