* Dropping singleton observations in PanelOLS models * Support for LSMR as an option to estimate parameters. LSMR can be much faster in very sparse unbalanced panels. * Added wald_test to panel model results class. * Added a low-memory option to limit memory usage when estimating models with 2 effects.
4.11
This is primarily a bug-fix release. Two bugs which incorrectly verified rank conditions on models were fixed. These checks affected:
* All asset pricing models * Fama-MacBeth panel data regression
In addition, an external dependency on cached-property was introduced.
4.10
This is a bug-fix release that fixes an incorrect implementation of the Parzen weight function. This release also contains small fixes for future changes in dependencies.
4.9
This is a minor release that focuses on fixes for upstream changes.
* Changed the return type of Wooldridge's over identification test when invalid to `InvalidTestStatistic` * Add typing information to IV models * Allow optimization parameters to be passed to `IVGMMCUE` * Removed internal use of pandas Panel * Improved performance in panel models when using `from_formula` * Switched to retaining index column names when original input index is named * Modified tests that were not well conceived * Added spell check to documentation build * Improve docstring for ``summary`` properties
4.8
This is a minor release with one feature and one bug fix:
* Corrected bug that prevented single character names in IV formulas * Corrected kappa estimation in LIML when there are no exogenous regressors
4.7
This is a minor release with one significant feature:
* Substantial performance improvements in PanelOLS and possibly other panel models for large dataset sizes