PyFixest 0.23.0
Hightlights
- PyFixest now includes Wald and F-Tests through the
wald_test()
method. - The new Wald Test feature enables us to provide basic IV diagnostics on the first stage, thanks to a significant overhaul of the
Feiv
class internals. - The
pf.etable()
function for regression output has been significantly enhanced for better aesthetics. - We've greatly improved the speed of the
predict()
method. - A new
panelview
function has been added to inspect staggered treatment rollouts in Difference-in-Differences studies. - We've introduced new arguments to
feols()
andfepois()
, including a "lean" argument to clear memory-heavy objects from Feols instances. - RI support has been added for the
rwolf
function, for experimenters who want to control the family-wise error rate of their tests. - An
update()
method has been implemented, which allows to update regression coefficients based on incoming data (useful for online learning setups). - Additionally, new vignettes on regression tables and using PyFixest with the marginaleffects package have been added.
Take a look at the quickstart notebook for a brief intro to all new features.
Breaking Changes
- We're adjusting the default small sample corrections to exactly match the
fixest
defaults, and a new vignette demonstrates equivalence between fitting models via R-fixest and py-fixest =) This change will lead to minor differences in computed standard errors and vcov's between versions 0.22.0 and 0.23.0.
New Contributors
- @Jayhyung made their first contribution in #514
- @asteves made their first contribution in #520
- @saidamir made their first contribution in #513
- @rafimikail made their first contribution in #528
- @greenguy33 made their first contribution in #527
- @b-knight made their first contribution in #551
What's Changed
- update readme files by @s3alfisc in #511
- type hints for vcov_utils by @s3alfisc in #512
- Add "ri" resampling method to Romano-Wolf procedure, by @Jayhyung in #514
- docs: add Jayhyung as a contributor for code by @allcontributors in #516
- Bump urllib3 from 2.2.1 to 2.2.2 by @dependabot in #517
- Fix Contributing document format issue by @asteves in #520
- docs: add asteves as a contributor for doc by @allcontributors in #521
- Add 1st stage regression in Feiv class by @Jayhyung in #525
- Added solver to feols and created new test file for it by @saidamir in #513
- docs: add saidamir as a contributor for code by @allcontributors in #530
- [Issue-400] Implementing dynamic alpha for coefplot and iplot by @rafimikail in #528
- docs: add rafimikail as a contributor for code by @allcontributors in #535
- Mention
self._vcov
in docs by @greenguy33 in #527 - docs: add greenguy33 as a contributor for code, and doc by @allcontributors in #532
- Bump certifi from 2024.6.2 to 2024.7.4 by @dependabot in #538
- Add Notebook on
Stargazer
andpymarginaleffects
support to the docs by @s3alfisc in #473 - fix typos by @s3alfisc in #540
- Add updates to wald_test method and unit testing files by @Jayhyung in #536
- Add
lean
function argument tofeols()
,fepois()
by @s3alfisc in #548 - Vcov by @s3alfisc in #529
- Bknight regex migration by @b-knight in #551
- add pure numpy predict function that speeds up ~40x by @apoorvalal in #553
- more fleshed-out panelview implementation by @apoorvalal in #552
- lsqr() for fixed effects solver by @greenguy33 in #546
- fix another all-contributors bug by @s3alfisc in #560
- docs: add b-knight as a contributor for code by @allcontributors in #561
- add statsmodels support for stargazer by @s3alfisc in #564
- Add (robust) F statistics of weak iv test and change 1st stage reg code by @Jayhyung in #563
- implement update method for coef vector by @apoorvalal in #567
- Remove Stargazer Dependency by @s3alfisc in #568
- update readme by @s3alfisc in #570
- Revert "update readme" by @s3alfisc in #572
- update quickstart for IV first stage, diagnostics, Wald tests by @s3alfisc in #569
- Update wls types tests by @s3alfisc in #562
- Rerun vignette by @s3alfisc in #575
- Release 0.23 by @s3alfisc in #576
Full Changelog: v0.22.2...v0.23.0