Reverse Transformation
Reverse transform standardized data to follow a non-standardized extreme value distribution (EVD).
revtrans.evd(z, threshold = NULL, location = NULL, scale, shape = NULL,
type = c("GEV", "GP", "PP", "Gumbel", "Weibull", "Frechet",
"Exponential", "Beta", "Pareto"))z |
numeric vector of data of length n following a standardized EVD. |
threshold |
number or numeric vector of length n giving the threshold, if applicable. |
location |
number or numeric vector of length n giving the location parameter(s), if applicable. |
scale |
number or or numeric vector of length n giving the scale parameter(s). |
shape |
number or numeric vector of length n giving the shape parameter(s), if applicable. |
type |
character string naming to what EVD should the data be reverse-transformed. Default is GEV df. |
For standardized EVD data (e.g., via trans), this function performs the reverse transformation back to the original scale.
numeric vector of length n.
Eric Gilleland
data(PORTw)
fit <- fevd(TMX1, PORTw, location.fun=~AOindex, units="deg C")
fit
z <- trans(fit)
fevd(z)
p <- findpars(fit)
y <- revtrans.evd(z=z, location=p$location, scale=2.6809613,
shape=-0.1812824)
fevd(y)
qqplot(y, PORTw$TMX1)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.