gevfit
Generalized extreme value parameter estimates
Syntax
parmhat = gevfit(X)
[parmhat,parmci] = gevfit(X)
[parmhat,parmci] = gevfit(X,alpha)
[...] = gevfit(X,alpha,options)
Description
parmhat = gevfit(X)
returns maximum likelihood estimates of the parameters for the generalized extreme value (GEV) distribution given the data in X.parmhat(1)
is the shape parameter,k
,parmhat(2)
is the scale parameter,sigma
, andparmhat(3)
is the location parameter,mu
.
[parmhat,parmci] = gevfit(X)
returns 95% confidence intervals for the parameter estimates.
[parmhat,parmci] = gevfit(X,alpha)
returns100(1-alpha)
% confidence intervals for the parameter estimates.
[...] = gevfit(X,alpha,options)
specifies control parameters for the iterative algorithm used to compute ML estimates. This argument can be created by a call tostatset
. Seestatset('gevfit')
for parameter names and default values. Pass in[]
foralpha
to use the default values.
Whenk < 0
, the GEV is the type III extreme value distribution. Whenk > 0
, the GEV distribution is the type II, or Frechet, extreme value distribution. Ifw
has a Weibull distribution as computed by thewblfit
function, then-w
has a type III extreme value distribution and1/w
has a type II extreme value distribution. In the limit ask
approaches 0, the GEV is the mirror image of the type I extreme value distribution as computed by theevfit
function.
The mean of the GEV distribution is not finite whenk
≥1
, and the variance is not finite whenk
≥1/2
. The GEV distribution is defined fork*(X-mu)/sigma > -1
.
References
[1] Embrechts, P., C. Klüppelberg, and T. Mikosch.Modelling Extremal Events for Insurance and Finance. New York: Springer, 1997.
[2] Kotz, S., and S. Nadarajah.Extreme Value Distributions: Theory and Applications. London: Imperial College Press, 2000.