Extreme Value Distribution |
(continuous probab. dist. for equations) |
Usage: |
ExtremeValueDist (x, a, b) |
Definition: |
exp (-exp (-(x-a)/b) - (x-a)/b) / b |
Parameters: |
a = location b = scale |
Required: |
b > 0 |
Moments: |
m = a + g b (g = Eulers = 0.5772156649) s = p b / sqrt(6) g1 = 1.3 b2 = 5.4 |
This distribution is the limiting distribution for the smallest or largest values in large samples drawn from a variety of distributions, including the normal distribution.
Also known as the "Fisher-Tippet distribution", "Fisher-Tippet Type I distribution" or the "log-Weibull distribution".