Release 4.28

This is a maintenance and compatibility release.

• Compatibility with formulaic 0.3.2 - 0.5.2
• Compatibility with pandas 2.0

Release 4.27

This is a bug fix and enhancement release.

• Switched from patsy for formulaic for linear constraint translation when using the formula interface.
• Fixed a bug when using escaped variable names, e.g., ``y ~ 1 + `x 3```, in panel data models.
• Fixed a bug that affected creating IV models using formulas with missing data.
• Fixed examples in the documentation.

Release 4.26

This is a minor release that addresses two issues:

• Fixed a bug in linearmodels.iv.model.IV2SLS and related models where linearmodels.iv.model.IV2SLS.predict would produce NaN values when exog and endog had different indices. An IndexWarning is now shown.
• Added stacklevel to all warnings to improve the accuracy of warning location.

Release 4.25

This release adds formulaic as the formula parser and fixes some minor bugs.

• Added formulaic as the preferred formula parser
• Clarified the null in the F-statistic
• Improved the error message when dependent and exog have different numbers of observations
• Fixed a bug in ACCovariance estimator where the number of observations was incorrectly overwritten
• Fixed a bug in PanelResults.corr_squared_between, lPanelResults.corr_squared_overall, and PanelResults.corr_squared_within where the correlation was not squared.

Release 4.24

This is a feature release. There are two new features:

• SystemResults.breusch_pagan implements the Breusch-Pagan test of 0 correlation (and so a diagonal covariance)
• SystemResults.likelihood_ratio implements a likelihood ratio test of a diagonal covariance (and so 0 correlation)

Release 4.23

This release fixes a bug that can affect standard error estimation in SUR and related models.

Release 4.22

This is a packaging-only release that fixes an issue with Windows wheels.

Release 4.21

This release fixes a technical issue the prevented wheels from being built. There are no other changes.

Release 4.20

This release fixes a single bug that affected the computation of the first-stage F-statistic.

Release 4.19

This is a minor release that fixes a wheel-building issue. There are no other changes from 4.18.