As several Extreme Value distributions are parameterized for high extreme values, reversed functions for minima (e.g. low flow statistics) are derived. Reversing is done by fitting to the negated data (x
), subtracting probabilities from one (1  f
) and computing the negated probabilities.
1 2 3  cdf_ev(distribution, x, para)
pel_ev(distribution, lmom, ...)
qua_ev(distribution, f, para)

distribution 
character vector of length one containing the name of the distribution. The family of the chosen distribution must be supported by the package lmom. See 
x 
Vector of quantiles. 
f 
Vector of probabilities. 
para 
Numeric vector containing the parameters of the distribution, in the order zeta, beta, delta (location, scale, shape). 
lmom 
Numeric vector containing the Lmoments of the distribution or of a data sample. E.g. as returned by 
... 
parameters like 
cdf_ev gives the distribution function; qua_ev gives the quantile function.
lmom
, cdfgev
, quagev
, pelgev
.
1 2 3 4 5 6 7 8 9 10  data("ngaruroro")
ng < as.xts(ngaruroro)
minima < as.vector(apply.yearly(ng$discharge, min, na.rm = TRUE))
# Weibull distribution and reversed GEV give the same results
distr < "wei"
qua_ev(distr, seq(0, 1, 0.1), para = pel_ev(distr, samlmu(minima)))
distr < "gevR"
qua_ev(distr, seq(0, 1, 0.1), para = pel_ev(distr, samlmu(minima)))

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.
All documentation is copyright its authors; we didn't write any of that.