Release 4.16.1

This is a version bump release to allow wheels to be rebuilt. There are not significant changes from 4.16.

Release Candidate for 4.16.1

This is a release candidate for a fixed 4.16.1 build

Release 4.16

This is a feature and big-fix release:

• Added APARCH volatilty process.
• Added support for Python 3.9 in pyproject.toml.
• Fixed a bug in the model degree-of-freedom calculation.
• Improved HARX initialization.

Release 4.15

This is a minor release with doc fixes and other small updates.

The only notable feature is PhillipsPerron.regression which returns regression results from the model estimated as part of the test.

Release 4.14

This is a feature and bug release.

New Features

Major

• There are two major new features: long-run covariance estimation and cointegration analysis
  • Added Kernel-based long-run variance estimation in arch.covariance.kernel. Examples include the
    arch.covariance.kernel.Bartlett and the arch.covariance.kernel.Parzen kernels. All estimators support
    automatic bandwidth selection.
  • Added Engle-Granger (arch.unitroot.cointegration.engle_granger) and Phillips-Ouliaris arch.unitroot.cointegration.phillips_ouliaris) cointegration tests
  • Added three methods to estimate cointegrating vectors: arch.unitroot.cointegration.CanonicalCointegratingReg, arch.unitroot.cointegration.DynamicOLS, and arch.unitroot.cointegration.FullyModifiedOLS.

Minor

• Issue warnings when unit root tests are mutated. Will raise after 5.0 is released.
• Improved exceptions in arch.unitroot.ADF, arch.unitroot.KPSS, arch.unitroot.PhillipsPerron, arch.unitroot.VarianceRatio, and arch.unitroot.ZivotAndrews when test specification is infeasible to the time series being too short or the required regression model having reduced rank.

Bugs Fixed

• Fixed a bug when using "bca" confidence intervals with extra_kwargs.
• Fixed a bug in arch.univariate.SkewStudent which did not use the user-provided RandomState when one was provided. This prevented reproducing simulated values.

Release 4.13

• Restore the vendored copy of property_cached which is required to build conda packages

Release 4.12

• Added typing support to all classes, functions, and methods.
• Fixed an issue that caused tests to fail on SciPy 1.4+.
• Dropped support for Python 3.5 inline with NEP 29.
• Added methods to compute moment and lower partial moments for standardized
  residuals. See, for example, SkewStudent.moment and SkewStudent.partial_moment.
• Fixed a bug that produced an OverflowError when a time series has no variance.

Release 4.11

This is a feature and bug release.

• Added ARCHModelResult.std_resid
• Error in bootstraps if inputs are not ndarrays, DataFrames or Series.
• Added a check that the covariance is non-zero when using "studentized" confidence intervals.
  If the function bootstrapped produces statistics with 0 variance, it is not possible to
  studentized.

Release 4.10

This release contains 2 big fixes.

• Fixed a bug in arch_lm_test that assumed that the model data is contained in
  a pandas Series.
• Fixed a bug that can affect use in certain environments that reload modules.

Release 4.9.1

This is a bug fix release:

• Fix an import bug that prevents conda packages from being built