Release 4.9.0

This is a feature and bug release.

• Removed support for Python 2.7.
• Added auto_bandwidth to compute optimized bandwidth for a number of common kernel covariance estimators. This code was written by Michael Rabba.
• Added a parameter rescale to arch_model that allows the estimator to rescale data if it may help parameter
  estimation. If rescale=True, then the data will be rescaled by a power of 10 (e.g., 10, 100, or 1000) to produce a series with a residual variance between 1 and 1000. The model is then estimated on the rescaled data. The scale is reported ARCHModelResult.scale. If rescale=None, a warning is produced if the data appear to be poorly scaled, but no change of scale is applied. If rescale=False, no scale change is applied and no warning is issued.
• Fixed a bug when using the BCA bootstrap method where the leave-one-out jackknife used the wrong centering variable.
• Added ARCHModelResult.optimization_result to simplify checking for convergence of the numerical optimizer.
• Added random_state argument to HARX.forecast to allow a RandomState objects to be passed in when forecasting when method='bootstrap'. This allows the repeatable forecast to be produced.
• Fixed a bug in VarianceRatio that used the wrong variance in nonrobust inference with overlapping samples.

Release 4.8.1

This is a small release that fixes an issue identified after 4.8.0 was released where extension modules would not be correctly imported.

Release 4.8

This is a feature and bug release. Highlights include:

• Added Zivot-Andrews unit root test.
• Added data dependent lag length selection to the KPSS test.
• Added IndependentSamplesBootstrap to bootstrap inference on statistics from independent samples that may
  have uneven length.
• Added arch_lm_test to ARCH-LM tests on model residuals or standardized residuals.
• Fixed a bug in ADF when applying to very short time series.
• Added ability to set the random_state when initializing a bootstrap.

Release 4.7

This is a feature and bug release:

• Added support for Fractionally Integrated GARCH (FIGARCH)
• Enable user to specify a specific value of the backcast in place of the automatically generated value.
• Fixed a big where parameter-less models where incorrectly reported as having constant variance

Release 4.6.0

This is a feature release with 1 new feature:

• Add support for MIDAS volatility processes with Hyperbolic weighting

Release 4.5.0

This is a feature release with 1 new feature:

• Added a parameter to forecast that allows a user-provided callable random
  generator to be used in place of the model random generator

Release 4.4.1

Packing only release to fix an issue on PyPi.

Release 4.4

This is a minor release containing mostly bug fixes.

Changes include:

• Added named parameters to Dickey-Fuller regressions.
• Removed use of the module-level NumPy RandomState. All random number generators use separate RandomState instances.
• Fixed a bug that prevented 1-step forecasts with exogenous regressors
• Added the Generalized Error Distribution for univariate ARCH models
• Fixed a bug in MCS when using the max method that prevented all included models from being listed

Release 4.3.1

• Fix GED in arch_model

Release 4.3

• Fixed a bug that prevented 1-step forecasts with exogenous regressors
• Added the Generalized Error Distribution for univariate ARCH models
• Fixed a bug in MCS when using the max method that prevented all included models from being
  listed
• Added FixedVariance volatility process which allows pre-specified variances to be used with
  a mean model. This has been added to allow so-called zig-zag estimation where a mean model is
  estimated with a fixed variance, and then a variance model is estimated on the residuals using
  a ZeroMean variance process.