GeneralizedParetoDistribution
statistics: GeneralizedParetoDistribution
Generalized Pareto probability distribution object.
A GeneralizedParetoDistribution
object consists of parameters, a
model description, and sample data for a Generalized Pareto probability
distribution.
The Generalized Pareto distribution is a continuous probability distribution that models the tail behavior of other distributions, commonly used for extreme value analysis. It is defined by shape parameter k, scale parameter sigma, and location parameter theta.
There are several ways to create a GeneralizedParetoDistribution
object.
fitdist
function.
makedist
function.
GeneralizedParetoDistribution (k,
sigma, theta)
to create a Generalized Pareto distribution with
fixed parameter values k, sigma, and theta.
GeneralizedParetoDistribution.fit
(x, theta, alpha, freq, options)
to fit a
distribution to the data in x using the same input arguments as the
gpfit
function.
It is highly recommended to use fitdist
and makedist
functions to create probability distribution objects, instead of the class
constructor or the aforementioned static method.
Further information about the Generalized Pareto distribution can be found at https://en.wikipedia.org/wiki/Generalized_Pareto_distribution
See also: fitdist, makedist, gpcdf, gpinv, gppdf, gprnd, gpfit, gplike, gpstat
Source Code: GeneralizedParetoDistribution
A scalar value characterizing the shape of the Generalized Pareto
distribution. You can access the k
property using dot name
assignment.
## Create a Generalized Pareto distribution with default parameters pd = makedist ("GeneralizedPareto") ## Query parameter 'k' (shape parameter) pd.k ## Set parameter 'k' pd.k = 0.5 ## Use this to initialize or modify the shape parameter of a Generalized Pareto ## distribution. The shape parameter can be any real scalar and determines the ## tail behavior (heavy-tailed if k>0). pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 1 sigma = 1 theta = 1 ans = 1 pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 1 theta = 1 |
## Create a Generalized Pareto distribution object by calling its constructor pd = GeneralizedParetoDistribution (0.5, 1, 0) ## Query parameter 'k' pd.k ## This demonstrates direct construction with a specific shape parameter, ## useful for modeling extreme values with known tail index. pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 1 theta = 0 ans = 0.5000 |
A positive scalar value characterizing the scale of the Generalized Pareto
distribution. You can access the sigma
property using dot name
assignment.
## Create a Generalized Pareto distribution with default parameters pd = makedist ("GeneralizedPareto") ## Query parameter 'sigma' (scale parameter) pd.sigma ## Set parameter 'sigma' pd.sigma = 2 ## Use this to initialize or modify the scale parameter in a Generalized Pareto ## distribution. The scale parameter must be a positive real scalar. pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 1 sigma = 1 theta = 1 ans = 1 pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 1 sigma = 2 theta = 1 |
## Create a Generalized Pareto distribution object by calling its constructor pd = GeneralizedParetoDistribution (0.5, 2, 0) ## Query parameter 'sigma' pd.sigma ## This shows how to set the scale parameter directly via the constructor, ## ideal for modeling the spread in extreme value data. pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 2 theta = 0 ans = 2 |
A scalar value characterizing the location of the Generalized Pareto
distribution. You can access the theta
property using dot name
assignment.
## Create a Generalized Pareto distribution with default parameters pd = makedist ("GeneralizedPareto") ## Query parameter 'theta' (location parameter) pd.theta ## Set parameter 'theta' pd.theta = 1 ## Use this to initialize or modify the location parameter in a Generalized Pareto ## distribution. The location parameter can be any real scalar, often set to a threshold in extreme value analysis. pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 1 sigma = 1 theta = 1 ans = 1 pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 1 sigma = 1 theta = 1 |
## Create a Generalized Pareto distribution object by calling its constructor pd = GeneralizedParetoDistribution (0.5, 1, 1) ## Query parameter 'theta' pd.theta ## This demonstrates setting the location parameter directly, useful for shifting the distribution in threshold-exceedance models. pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 1 theta = 1 ans = 1 |
A character vector specifying the name of the probability distribution object. This property is read-only.
A scalar integer value specifying the number of parameters characterizing the probability distribution. This property is read-only.
A cell array of character vectors with each element containing the name of a distribution parameter. This property is read-only.
A cell array of character vectors with each element containing a short description of a distribution parameter. This property is read-only.
A numeric vector containing the values of the distribution
parameters. This property is read-only. You can change the distribution
parameters by assigning new values to the k
, sigma
, and
theta
properties.
A numeric matrix containing the variance-covariance of the parameter estimates. Diagonal elements contain the variance of each estimated parameter, and non-diagonal elements contain the covariance between the parameter estimates. The covariance matrix is only meaningful when the distribution was fitted to data. If the distribution object was created with fixed parameters, or a parameter of a fitted distribution is modified, then all elements of the variance-covariance are zero. This property is read-only.
A logical vector specifying which parameters are fixed and
which are estimated. true
values correspond to fixed parameters,
false
values correspond to parameter estimates. This property is
read-only.
A numeric vector specifying the truncation interval for the
probability distribution. First element contains the lower boundary,
second element contains the upper boundary. This property is read-only.
You can only truncate a probability distribution with the
truncate
method.
A logical scalar value specifying whether a probability distribution is truncated or not. This property is read-only.
A scalar structure containing the following fields:
data
: a numeric vector containing the data used for
distribution fitting.
cens
: a numeric vector of logical values indicating
censoring information corresponding to the elements of the data used for
distribution fitting. If no censoring vector was used for distribution
fitting, then this field defaults to an empty array.
freq
: a numeric vector of non-negative integer values
containing the frequency information corresponding to the elements of the
data used for distribution fitting. If no frequency vector was used for
distribution fitting, then this field defaults to an empty array.
GeneralizedParetoDistribution: p = cdf (pd, x)
GeneralizedParetoDistribution: p = cdf (pd, x, "upper"
)
p = cdf (pd, x)
computes the CDF of the
probability distribution object, pd, evaluated at the values in
x.
p = cdf (…,
returns the complement of
the CDF of the probability distribution object, pd, evaluated at
the values in x.
"upper"
)
## Plot various CDFs from the Generalized Pareto distribution x = 0:0.01:5; pd1 = makedist ("GeneralizedPareto", "k", 0.2, "sigma", 1, "theta", 0); pd2 = makedist ("GeneralizedPareto", "k", 0.5, "sigma", 1, "theta", 0); pd3 = makedist ("GeneralizedPareto", "k", 0.8, "sigma", 1, "theta", 0); p1 = cdf (pd1, x); p2 = cdf (pd2, x); p3 = cdf (pd3, x); plot (x, p1, "-b", x, p2, "-g", x, p3, "-r") grid on legend ({"k = 0.2, sigma = 1, theta = 0", "k = 0.5, sigma = 1, theta = 0", "k = 0.8, sigma = 1, theta = 0"}, ... "location", "southeast") title ("Generalized Pareto CDF") xlabel ("Exceedance value") ylabel ("Cumulative probability") ## Use this to compute and visualize the cumulative distribution function ## for different Generalized Pareto distributions, showing how probability ## accumulates over exceedance values in extreme value modeling. |
GeneralizedParetoDistribution: x = icdf (pd, p)
x = icdf (pd, p)
computes the quantile (the
inverse of the CDF) of the probability distribution object, pd,
evaluated at the values in p.
## Plot various iCDFs from the Generalized Pareto distribution p = 0.001:0.001:0.999; pd1 = makedist ("GeneralizedPareto", "k", 0.2, "sigma", 1, "theta", 0); pd2 = makedist ("GeneralizedPareto", "k", 0.5, "sigma", 1, "theta", 0); pd3 = makedist ("GeneralizedPareto", "k", 0.8, "sigma", 1, "theta", 0); x1 = icdf (pd1, p); x2 = icdf (pd2, p); x3 = icdf (pd3, p); plot (p, x1, "-b", p, x2, "-g", p, x3, "-r") grid on legend ({"k = 0.2, sigma = 1, theta = 0", "k = 0.5, sigma = 1, theta = 0", "k = 0.8, sigma = 1, theta = 0"}, ... "location", "northwest") title ("Generalized Pareto iCDF") xlabel ("Probability") ylabel ("Exceedance value") ## This demonstrates the inverse CDF (quantiles) for Generalized Pareto ## distributions, useful for finding the exceedance value corresponding to ## given return probabilities in risk assessment. |
GeneralizedParetoDistribution: r = iqr (pd)
r = iqr (pd)
computes the interquartile range of the
probability distribution object, pd.
## Compute the interquartile range for a Generalized Pareto distribution pd = makedist ("GeneralizedPareto", "k", 0.5, "sigma", 1, "theta", 0) iqr_value = iqr (pd) ## Use this to calculate the interquartile range, which measures the spread ## of the middle 50% of the distribution, useful for understanding variability ## in exceedance values. pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 1 theta = 0 iqr_value = 1.6906 |
GeneralizedParetoDistribution: m = mean (pd)
m = mean (pd)
computes the mean of the probability
distribution object, pd.
## Compute the mean for different Generalized Pareto distributions pd1 = makedist ("GeneralizedPareto", "k", 0.2, "sigma", 1, "theta", 0); pd2 = makedist ("GeneralizedPareto", "k", 0.4, "sigma", 1, "theta", 0); mean1 = mean (pd1) mean2 = mean (pd2) ## This shows how to compute the expected exceedance value for Generalized Pareto ## distributions with different shape parameters (note: mean is finite only if k<1). mean1 = 1.2500 mean2 = 1.6667 |
GeneralizedParetoDistribution: m = median (pd)
m = median (pd)
computes the median of the probability
distribution object, pd.
## Compute the median for different Generalized Pareto distributions pd1 = makedist ("GeneralizedPareto", "k", 0.2, "sigma", 1, "theta", 0); pd2 = makedist ("GeneralizedPareto", "k", 0.5, "sigma", 1, "theta", 0); median1 = median (pd1) median2 = median (pd2) ## Use this to find the median exceedance value, which splits the distribution ## into two equal probability halves. median1 = 0.7435 median2 = 0.8284 |
GeneralizedParetoDistribution: nlogL = negloglik (pd)
nlogL = negloglik (pd)
computes the negative
loglikelihood of the probability distribution object, pd.
## Compute the negative loglikelihood for a fitted Generalized Pareto distribution pd = makedist ("GeneralizedPareto", "k", 0.5, "sigma", 1, "theta", 0) rand ("seed", 21); data = random (pd, 100, 1); pd_fitted = GeneralizedParetoDistribution.fit (data, 0) nlogL = negloglik (pd_fitted) ## This is useful for assessing the fit of a Generalized Pareto distribution to ## data, lower values indicate a better fit. pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 1 theta = 0 pd_fitted = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.605009 [0.327245, 0.882774] sigma = 0.958583 [0.697048, 1.31825] theta = 0 nlogL = -156.27 |
GeneralizedParetoDistribution: ci = paramci (pd)
GeneralizedParetoDistribution: ci = paramci (pd, Name, Value)
ci = paramci (pd)
computes the lower and upper
boundaries of the 95% confidence interval for each parameter of the
probability distribution object, pd.
ci = paramci (pd, Name, Value)
computes the
confidence intervals with additional options specified by
Name-Value
pair arguments listed below.
Name | Value | |
---|---|---|
"Alpha" | A scalar value in the range specifying the significance level for the confidence interval. The default value 0.05 corresponds to a 95% confidence interval. | |
"Parameter" | A character vector or a cell array of
character vectors specifying the parameter names for which to compute
confidence intervals. By default, paramci computes confidence
intervals for all distribution parameters. |
paramci
is meaningful only when pd is fitted to data,
otherwise an empty array, []
, is returned.
## Compute confidence intervals for parameters of a fitted Generalized Pareto ## distribution pd = makedist ("GeneralizedPareto", "k", 0.5, "sigma", 1, "theta", 0) rand ("seed", 21); data = random (pd, 1000, 1); [phat, ci] = gpfit (data, 0, 0.05, []); disp ("Estimated parameters (k, sigma, theta):"), disp (phat) disp ("95% Confidence Intervals for k and sigma:"), disp (ci) ## Use this to obtain confidence intervals for the estimated parameters (k and sigma), ## providing a range of plausible values given the data (theta is fixed). pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 1 theta = 0 Estimated parameters (k, sigma, theta): 0.5061 0.9545 0 95% Confidence Intervals for k and sigma: 0.4156 0.8592 0 0.5967 1.0603 0 |
GeneralizedParetoDistribution: y = pdf (pd, x)
y = pdf (pd, x)
computes the PDF of the
probability distribution object, pd, evaluated at the values in
x.
## Plot various PDFs from the Generalized Pareto distribution x = 0:0.01:5; pd1 = makedist ("GeneralizedPareto", "k", 0.2, "sigma", 1, "theta", 0); pd2 = makedist ("GeneralizedPareto", "k", 0.5, "sigma", 1, "theta", 0); pd3 = makedist ("GeneralizedPareto", "k", 0.8, "sigma", 1, "theta", 0); y1 = pdf (pd1, x); y2 = pdf (pd2, x); y3 = pdf (pd3, x); plot (x, y1, "-b", x, y2, "-g", x, y3, "-r") grid on legend ({"k = 0.2, sigma = 1, theta = 0", "k = 0.5, sigma = 1, theta = 0", "k = 0.8, sigma = 1, theta = 0"}, ... "location", "northeast") title ("Generalized Pareto PDF") xlabel ("Exceedance value") ylabel ("Probability density") ## This visualizes the probability density function for Generalized Pareto ## distributions, showing the likelihood of different exceedance values. |
GeneralizedParetoDistribution: plot (pd)
GeneralizedParetoDistribution: plot (pd, Name, Value)
GeneralizedParetoDistribution: h = plot (…)
plot (pd)
plots a probability density function (PDF) of the
probability distribution object pd. If pd contains data,
which have been fitted by fitdist
, the PDF is superimposed over a
histogram of the data.
plot (pd, Name, Value)
specifies additional
options with the Name-Value
pair arguments listed below.
Name | Value | |
---|---|---|
"PlotType" | A character vector specifying the plot
type. "pdf" plots the probability density function (PDF). When
pd is fit to data, the PDF is superimposed on a histogram of the
data. "cdf" plots the cumulative density function (CDF). When
pd is fit to data, the CDF is superimposed over an empirical CDF.
"probability" plots a probability plot using a CDF of the data
and a CDF of the fitted probability distribution. This option is
available only when pd is fitted to data. | |
"Discrete" | A logical scalar to specify whether to
plot the PDF or CDF of a discrete distribution object as a line plot or a
stem plot, by specifying false or true , respectively. By
default, it is true for discrete distributions and false
for continuous distributions. When pd is a continuous distribution
object, option is ignored. | |
"Parent" | An axes graphics object for plot. If
not specified, the plot function plots into the current axes or
creates a new axes object if one does not exist. |
h = plot (…)
returns a graphics handle to the plotted
objects.
## Create a Generalized Pareto distribution with fixed parameters k = 0.5, sigma = 1, theta = 0 ## and plot its PDF. pd = makedist ("GeneralizedPareto", "k", 0.3, "sigma", 1, "theta", 0) plot (pd) title ("Fixed Generalized Pareto distribution with k = 0.3, sigma = 1, theta = 0") pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.3 sigma = 1 theta = 0 |
## Generate a data set of 100 random samples from a Generalized Pareto ## distribution with parameters k = 0.5, sigma = 1, theta = 0. Fit a Generalized Pareto ## distribution to this data (fixing theta=0) and plot its CDF superimposed over an empirical ## CDF. pd_fixed = makedist ("GeneralizedPareto", "k", 0.5, "sigma", 1, "theta", 0) rand ("seed", 21); data = random (pd_fixed, 100, 1); pd_fitted = GeneralizedParetoDistribution.fit (data, 0) plot (pd_fitted, "PlotType", "cdf") txt = "Fitted Generalized Pareto distribution with k = %0.2f, sigma = %0.2f, theta = 0"; title (sprintf (txt, pd_fitted.k, pd_fitted.sigma)) legend ({"empirical CDF", "fitted CDF"}, "location", "southeast") ## Use this to visualize the fitted CDF compared to the empirical CDF of the ## data, useful for assessing model fit in extreme value analysis. pd_fixed = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 1 theta = 0 pd_fitted = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.605009 [0.327245, 0.882774] sigma = 0.958583 [0.697048, 1.31825] theta = 0 |
## Generate a data set of 200 random samples from a Generalized Pareto ## distribution with parameters k = 0.5, sigma = 1, theta = 0. Display a probability ## plot for the Generalized Pareto distribution fit to the data (fixing theta=0). pd_fixed = makedist ("GeneralizedPareto", "k", 0.5, "sigma", 1, "theta", 0) rand ("seed", 21); data = random (pd_fixed, 200, 1); pd_fitted = GeneralizedParetoDistribution.fit (data, 0) plot (pd_fitted, "PlotType", "probability") txt = strcat ("Probability plot of fitted Generalized Pareto", ... " distribution with k = %0.2f, sigma = %0.2f, theta = 0"); title (sprintf (txt, pd_fitted.k, pd_fitted.sigma)) legend ({"empirical CDF", "fitted CDF"}, "location", "southeast") ## This creates a probability plot to compare the fitted distribution to the ## data, useful for checking if the Generalized Pareto model is appropriate for tails. pd_fixed = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 1 theta = 0 pd_fitted = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.571492 [0.367911, 0.775073] sigma = 0.907212 [0.718512, 1.14547] theta = 0 |
GeneralizedParetoDistribution: [nlogL, param] = proflik (pd, pnum)
GeneralizedParetoDistribution: [nlogL, param] = proflik (pd, pnum, "Display"
, display)
GeneralizedParetoDistribution: [nlogL, param] = proflik (pd, pnum, setparam)
GeneralizedParetoDistribution: [nlogL, param] = proflik (pd, pnum, setparam, "Display"
, display)
[nlogL, param] = proflik (pd, pnum)
returns a vector nlogL of negative loglikelihood values and a
vector param of corresponding parameter values for the parameter in
the position indicated by pnum. By default, proflik
uses
the lower and upper bounds of the 95% confidence interval and computes
100 equispaced values for the selected parameter. pd must be
fitted to data.
[nlogL, param] = proflik (pd, pnum,
also plots the profile likelihood
against the default range of the selected parameter.
"Display"
, "on"
)
[nlogL, param] = proflik (pd, pnum,
setparam)
defines a user-defined range of the selected parameter.
[nlogL, param] = proflik (pd, pnum,
setparam,
also plots the profile
likelihood against the user-defined range of the selected parameter.
"Display"
, "on"
)
For the Generalized Pareto distribution, pnum = 1
selects
the parameter k
, pnum = 2
selects the parameter
sigma
, and pnum = 3
selects the parameter
theta
.
When opted to display the profile likelihood plot, proflik
also
plots the baseline loglikelihood computed at the lower bound of the 95%
confidence interval and estimated maximum likelihood. The latter might
not be observable if it is outside of the used-defined range of parameter
values.
## Compute and plot the profile likelihood for the shape parameter of a fitted ## Generalized Pareto distribution pd = makedist ("GeneralizedPareto", "k", 0.5, "sigma", 1, "theta", 0) rand ("seed", 21); data = random (pd, 1000, 1); pd_fitted = GeneralizedParetoDistribution.fit (data, 0) [nlogL, param] = proflik (pd_fitted, 1, "Display", "on"); ## Use this to analyze the profile likelihood of the shape parameter (k), ## helping to understand the uncertainty in parameter estimates for tail behavior. pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 1 theta = 0 pd_fitted = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.506107 [0.415558, 0.596656] sigma = 0.9545 [0.85923, 1.06033] theta = 0 |
GeneralizedParetoDistribution: r = random (pd)
GeneralizedParetoDistribution: r = random (pd, rows)
GeneralizedParetoDistribution: r = random (pd, rows, cols, …)
GeneralizedParetoDistribution: r = random (pd, [sz])
r = random (pd)
returns a random number from the
distribution object pd.
When called with a single size argument, random
returns a square
matrix with the dimension specified. When called with more than one
scalar argument, the first two arguments are taken as the number of rows
and columns and any further arguments specify additional matrix
dimensions. The size may also be specified with a row vector of
dimensions, sz.
## Generate random samples from a Generalized Pareto distribution pd = makedist ("GeneralizedPareto", "k", 0.5, "sigma", 1, "theta", 0) rand ("seed", 25); samples = random (pd, 500, 1); hist (samples, 50) title ("Histogram of 500 random samples from GeneralizedPareto(k=0.5, sigma=1, theta=0)") xlabel ("Exceedance value") ylabel ("Frequency") ## This generates random samples from a Generalized Pareto distribution, useful ## for simulating extreme exceedances in risk modeling. pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 1 theta = 0 |
GeneralizedParetoDistribution: s = std (pd)
s = std (pd)
computes the standard deviation of the
probability distribution object, pd.
## Compute the standard deviation for a Generalized Pareto distribution pd = makedist ("GeneralizedPareto", "k", 0.3, "sigma", 1, "theta", 0) std_value = std (pd) ## Use this to calculate the standard deviation, which measures the variability ## in exceedance values (finite only if k<0.5). pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.3 sigma = 1 theta = 0 std_value = 2.2588 |
GeneralizedParetoDistribution: t = truncate (pd, lower, upper)
t = truncate (pd, lower, upper)
returns a
probability distribution t, which is the probability distribution
pd truncated to the specified interval with lower limit, lower,
and upper limit, upper. If pd is fitted to data with
fitdist
, the returned probability distribution t is not
fitted, does not contain any data or estimated values, and it is as it
has been created with the makedist function, but it includes the
truncation interval.
## Plot the PDF of a Generalized Pareto distribution, with parameters k = 0.5, sigma = 1, theta = 0, ## truncated at [0.5, 2] intervals. Generate 10000 random samples from this truncated distribution ## and superimpose a histogram scaled accordingly pd = makedist ("GeneralizedPareto", "k", 0.5, "sigma", 1, "theta", 0) t = truncate (pd, 0.5, 2) rand ("seed", 21); data = random (t, 10000, 1); ## Plot histogram and fitted PDF plot (t) hold on hist (data, 100, 50) hold off title ("Generalized Pareto distribution (k = 0.5, sigma = 1, theta = 0) truncated at [0.5, 2]") legend ("Truncated PDF", "Histogram") ## This demonstrates truncating a Generalized Pareto distribution to a specific ## range and visualizing the resulting distribution with random samples. pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 1 theta = 0 t = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.5 sigma = 1 theta = 0 Truncated to the interval [0.5, 2] |
GeneralizedParetoDistribution: v = var (pd)
v = var (pd)
computes the variance of the
probability distribution object, pd.
## Compute the variance for a Generalized Pareto distribution pd = makedist ("GeneralizedPareto", "k", 0.3, "sigma", 1, "theta", 0) var_value = var (pd) ## Use this to calculate the variance, which quantifies the spread of the ## exceedance values in the distribution (finite only if k<0.5). pd = GeneralizedParetoDistribution Generalized Pareto distribution k = 0.3 sigma = 1 theta = 0 var_value = 5.1020 |