Skip to content

Commit

Permalink
Gelbach Decomposition (#669)
Browse files Browse the repository at this point in the history
* initial commit

* add tqdm

* add agg argument to suppres aggregation of mediators

* parallelize

* update lock

* some speed ups for the cluster bootstrap

* GelbachDecomposition data class

* add examples, run linter

* checks for combine_covariates

* reformat

* reformat table output

* parallel bootstrap

* fix linting

* add basic tests

* some cleanups

* add decompose error checks

* more cleanups

* support regex

* delete coverage

* relax test condition

* fix type checks

* fix small bug introduced in prev commit

* delete cov files

* add aggregate first algo

* add no inference option

* delete cov

* handle joblib dependency, rename inference arg to only_coef for compatibility with fixest

* bring back tests

* Use sparse solver

* cleanup

* fix small bug, back to dense matrices if agg_first = False

* trigger additional decompose error

* add tests against stata

* delete coverage

* fix inference bug

* fix bug with intercepts

* dont check cis

* use self.X1 etc in bootstrap

* Update changelog

* one hot encode fixed effects, revert changes in 43b8e79

* fix bug with combine_covariates = None

* cleanup

* cleanup

* readme updates

* joblib as dep

* update docs

* import re

* update docs

* wildboottest doc bug

* fix doc bug with wildboottest

* yet another test bug
  • Loading branch information
s3alfisc authored Dec 1, 2024
1 parent ce4efd3 commit 25826bc
Show file tree
Hide file tree
Showing 18 changed files with 5,477 additions and 2,587 deletions.
2 changes: 2 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,8 @@ For questions on `PyFixest`, head on over to our [PyFixest Discourse forum](http
- **Multiple Hypothesis Corrections** following the Procedure by [Romano and Wolf](https://journals.sagepub.com/doi/pdf/10.1177/1536867X20976314) and **Simultaneous Confidence Intervals** using a **Multiplier Bootstrap**
- Fast **Randomization Inference** as in the [ritest Stata package](https://hesss.org/ritest.pdf)
- The **Causal Cluster Variance Estimator (CCV)** following [Abadie et al.](https://economics.mit.edu/sites/default/files/2022-09/When%20Should%20You%20Adjust%20Standard%20Errors%20for%20Clustering.pdf)
- Regression **Decomposition** following [Gelbach (2016)](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=1425737)
- **Publication-ready tables** with [Great Tables](https://posit-dev.github.io/great-tables/articles/intro.html) or LaTex booktabs


## Installation
Expand Down
Loading

0 comments on commit 25826bc

Please sign in to comment.