We have already tried the distribution fitting of GEV with L-moments on sample data provided in the extRemes package (Potomac River data), and we have obtained our location, scale, and shape parameters. We do not know how to proceed in goodness-of-fit testing and quantile estimation for 5-, 10-, and 20- year return periods. Any tips and suggestions to our problems would be of great help for the progress of our thesis.
data("Potomac")
fevd(Flow, Potomac, type = c("GEV"), method = c("Lmoments"), 106)
fitevd = fevd(Flow, Potomac, type = c("GEV"), method = c("Lmoments"), 106)
df = pevd(Potomac$Flow, loc = 8.693596e+04, scale = 4.135809e+04,
shape = 2.164866e-01, threshold = 1, lambda = 1, type = c("GEV"),
lower.tail = TRUE, log.p = FALSE)
ci(fitevd, alpha = 0.05, type = c("return.level"), return.period = 2, which.par, R = 502)