请教高手，如何在matlab中做非线性的极大似然参数估计？

help gppdf
GPPDF Generalized Pareto probability density function (pdf).
    Y = GPPDF(X,K,SIGMA,THETA) returns the pdf of the generalized Pareto (GP)
    distribution with tail index (shape) parameter K, scale parameter SIGMA,
    and threshold (location) parameter THETA, evaluated at the values in X.
    The size of Y is the common size of the input arguments.  A scalar input
    functions as a constant matrix of the same size as the other inputs.

    Default values for K, SIGMA, and THETA are 0, 1, and 0, respectively.

    When K = 0 and THETA = 0, the GP is equivalent to the exponential
    distribution.  When K > 0 and THETA = SIGMA/K, 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.

    See also gpcdf, gpfit, gpinv, gplike, gprnd, gpstat, pdf.

    Reference page in Help browser
       doc gppdf