能 有pareto 分布的定义 查看matlab statToolbox 相关说明

我是个新手, 请你说的详细点好吗?  谢谢了

Generalized Pareto DistributionThe Generalized Pareto distribution is used to model the tails of a
data distribution.The following distribution functions have been added:gpcdf — Cumulative
distribution functiongpfit — Parameter
estimation functiongpinv — Inverse
cumulative distribution functiongplike — Negative
log-likelihood functiongppdf — Probability
density functiongprnd — Random
number generatorgpstat — Distribution
statistics

谢谢你啊

我使用极大似然估计  phat,pci]=mle('gp',x,2.5)
??? Error using ==> mle
Sorry, MLE cannot estimate parameters from this distribution.

请问什么地方有错误呢?

线上等

[em04][em04][em04][em04]

还是给你回答了吧

parmhat = gpfit(X) 产生pareto随机数

参数估计，

[parmhat,parmci] = gpfit(X) 

参数估计，有alpha

[parmhat,parmci] = gpfit(X,alpha)

 GPFIT Parameter estimates and confidence intervals for generalized Pareto data.
    PARMHAT = GPFIT(X) returns maximum likelihood estimates of the parameters
    of the two-parameter generalized Pareto (GP) distribution given the data
    in X.  PARMHAT(1) is the tail index (shape) parameter, K and PARMHAT(2) is
    the scale parameter, SIGMA.  GPFIT does not fit a threshold (location)
    parameter.
 
    [PARMHAT,PARMCI] = GPFIT(X) returns 95% confidence intervals for the
    parameter estimates.
 
    [PARMHAT,PARMCI] = GPFIT(X,ALPHA) returns 100(1-ALPHA) percent confidence
    intervals for the parameter estimates.
 
    [...] = GPFIT(X,ALPHA,OPTIONS) specifies control parameters for the
    iterative algorithm used to compute ML estimates. This argument can be
    created by a call to STATSET.  See STATSET('gpfit') for parameter names
    and default values.
 
    Pass in [] for ALPHA to use the default values.
 
    Other functions for the generalized Pareto, such as GPCDF, allow a
    threshold parameter THETA.  However, GPFIT does not estimate THETA, and it
    must be assumed known, and subtracted from X before calling GPFIT.
 
    When K = 0 and THETA = 0, the GP is equivalent to the exponential
    distribution.  When K > 0 and THETA = SIGMA, the GP is equivalent to the
    Pareto distribution. The mean of the GP is not finite when K >= 1, and the
    variance is not finite when K >= 1/2.  When K >= 0, the GP has positive
    density for X>THETA, or, when K < 0, for 0 <= (X-THETA)/SIGMA <= -1/K.