I need to fit a generalised extreme value distribution to my data but I want the ability to perform generalised linear modelling of the parameters, particularly the location. Can anyone recommend the best method/R package for doing this? Thanks

  • $\begingroup$ Since (to my understanding) the GEV isn't exponential family, what do you intend when you say "generalized linear modelling"? $\endgroup$
    – Glen_b
    Dec 15, 2014 at 2:21

1 Answer 1


I'm fairly new to R, but for my research I have to deal with extreme values, so maybe what I found can help you.

  1. You need to install the evd package.
  2. Then you can use the function fgev (assuming you are using generalized extreme value distribution) and specify the location that you want, like this:

    M <- fgev(uvdata, location = 0, scale = 1, shape = 0)

The first argument is your data, then you can specify the other parameters you need.


Not the answer you're looking for? Browse other questions tagged or ask your own question.