arch.univariate.GeneralizedError

class arch.univariate.GeneralizedError(random_state=None, *, seed=None)[source]

Generalized Error distribution for use with ARCH models

Parameters
random_stateRandomState, optional

Deprecated since version 5.0: random_state is deprecated. Use seed instead.

seed{int, Generator, RandomState}, optional

Random number generator instance or int to use. Set to ensure reproducibility. If using an int, the argument is passed to np.random.default_rng. If not provided, default_rng is used with system-provided entropy.

Attributes
generator

The NumPy Generator or RandomState attached to the distribution

name

The name of the distribution

random_state

The NumPy RandomState attached to the distribution

Methods

bounds(resids)

Parameter bounds for use in optimization.

cdf(resids[, parameters])

Cumulative distribution function

constraints()

Construct arrays to use in constrained optimization.

loglikelihood(parameters, resids, sigma2[, …])

Computes the log-likelihood of assuming residuals are have a Generalized Error Distribution, conditional on the variance.

moment(n[, parameters])

Moment of order n

parameter_names()

Names of distribution shape parameters

partial_moment(n[, z, parameters])

Order n lower partial moment from -inf to z

ppf(pits[, parameters])

Inverse cumulative density function (ICDF)

simulate(parameters)

Simulates i.i.d.

starting_values(std_resid)

Construct starting values for use in optimization.

Methods

bounds(resids)

Parameter bounds for use in optimization.

cdf(resids[, parameters])

Cumulative distribution function

constraints()

Construct arrays to use in constrained optimization.

loglikelihood(parameters, resids, sigma2[, …])

Computes the log-likelihood of assuming residuals are have a Generalized Error Distribution, conditional on the variance.

moment(n[, parameters])

Moment of order n

parameter_names()

Names of distribution shape parameters

partial_moment(n[, z, parameters])

Order n lower partial moment from -inf to z

ppf(pits[, parameters])

Inverse cumulative density function (ICDF)

simulate(parameters)

Simulates i.i.d.

starting_values(std_resid)

Construct starting values for use in optimization.

Properties

generator

The NumPy Generator or RandomState attached to the distribution

name

The name of the distribution

random_state

The NumPy RandomState attached to the distribution