=========
Version 5
=========

Release 5.6
===========
- Fix a bug in ``forecast`` forecasting from a model with lagged dependent
  variables (e.g., AR) with rescaled data (either ``rescale=True`` or when
  using automatic rescaling).  (:issue:`632`)

Release 5.5
===========
- NumPy 1.25 fixes
- Initial pandas copy-on-write support
- Switched doc theme to sphinx-immaterial
- Small fixes for typing issues

Release 5.4
===========
- Compatability release with pandas 2.0
- Add testing and wheel support for Python 3.11

Release 5.3
===========
- Fixed a bug in :func:`~arch.univariate.mean.arch_model` where ``power`` was
  not passed to the :class:`~arch.univariate.FIGARCH` constructor (:issue:`572`).
- Fixed a bug that affected downstream projects due to an overly specific assert
  (:issue:`569`).

Release 5.2
===========
- Fixed a bug in in :func:`~arch.univariate.base.ARCHModelResult.std_resid` that
  would raise an exception when the data used to construct the model with a NumPy
  array (:issue:`565`).
- Fixed a bug in :func:`~arch.univariate.base.ARCHModelResult.forecast` and related
  ``forecast`` methods when producing multi-step forecasts usign simulation with
  exogenous variables (:issue:`551`).

Release 5.1
===========

Unit Root
~~~~~~~~~

- Improved automatic lag length selection in :class:`~arch.unitroot.DFGLS`
  by using OLS rather than GLS detrended data when selecting the lag length.
  This problem was studied by Perron, P., & Qu, Z. (2007).

Release 5.0
===========

Unit Root
~~~~~~~~~
- All unit root tests are now immutable, and so properties such as ``trend`` cannot
  be set after the test is created.

Bootstrap
~~~~~~~~~
- Added ``seed`` keyword argument to all bootstraps (e.g., :class:`~arch.bootstrap.IIDBootstrap`
  and :class:`~arch.bootstrap.StationaryBootstrap`) that allows a NumPy :class:`numpy.random.Generator`
  to be used. The ``seed`` keyword argument also accepts legacy :class:`numpy.random.RandomState`
  instances and integers.  If an integer is passed, the random number generator is constructed by
  calling :func:`numpy.random.default_rng` The ``seed`` keyword argument replaces the
  ``random_state`` keyword argument.
- The :func:`~arch.bootstrap.IIDBootstrap.random_state` property has also been deprecated in favor
  of :func:`~arch.bootstrap.IIDBootstrap.generator`.
- The :func:`~arch.bootstrap.IIDBootstrap.get_state` and :func:`~arch.bootstrap.IIDBootstrap.set_state`
  methods have been replaced by the :func:`~arch.bootstrap.IIDBootstrap.state` property.

Volatility Modeling
~~~~~~~~~~~~~~~~~~~
- Added ``seed`` keyword argument to all distributions (e.g., :class:`~arch.univariate.distribution.Normal`
  and :class:`~arch.univariate.distribution.StudentsT`) that allows a NumPy :class:`numpy.random.Generator`
  to be used. The ``seed`` keyword argument also accepts legacy :class:`numpy.random.RandomState`
  instances and integers.  If an integer is passed, the random number generator is constructed by
  calling :func:`numpy.random.default_rng` The ``seed`` keyword argument replaces the
  ``random_state`` keyword argument.
- The :func:`~arch.univariate.distribution.Normal.random_state` property has also been deprecated in favor
  of :func:`~arch.univariate.distribution.Normal.generator`.
- Added :class:`~arch.univariate.ARCHInMean` mean process supporting (G)ARCH-in-mean models.
- Extended :class:`~arch.univariate.volatility.VolatilityProcess` with
  :func:`~arch.univariate.volatility.VolatilityProcess.volatility_updater` that contains a
  :class:`~arch.univariate.recursions_python.VolatilityUpdater` to allow
  :class:`~arch.univariate.ARCHInMean` to be created from different volatility processes.

Setup
~~~~~
- Added support for using an environmental variable to disable C-extension compilation.

  * Linux and OSX: ``export ARCH_NO_BINARY=1``
  * PowerShell: ``$env:ARCH_NO_BINARY=1``
  * cmd: ``set ARCH_NO_BINARY=1``
