Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion DESCRIPTION
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,6 @@ BugReports: https://github.com/lrberge/fixest/issues
URL: https://lrberge.github.io/fixest/, https://github.com/lrberge/fixest
VignetteBuilder: knitr
LazyData: true
RoxygenNote: 7.3.2.9000
RoxygenNote: 7.3.3
Roxygen: list(markdown = TRUE)
Encoding: UTF-8
4 changes: 4 additions & 0 deletions NAMESPACE
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,8 @@ export(extralines_register)
# misc funs
export(collinearity)
export(r2, fitstat, fitstat_register, wald)
# AR test
export(ar_test, ar_confint)
export(fixest_startup_msg)
export(check_conv_feols)
export(demeaning_algo)
Expand Down Expand Up @@ -74,6 +76,8 @@ export(esttex, esttable)
# Base methods
S3method(print, fixest)
S3method(print, fixest_fitstat)
S3method(print, fixest_ar)
S3method(print, fixest_ar_confint)
S3method(print, vec_n_unik)
S3method(print, list_n_unik)
S3method(print, osize)
Expand Down
2 changes: 2 additions & 0 deletions NEWS.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,8 @@

## New features

- Added Anderson-Rubin (AR) weak-IV robust test for `feols` IV models via `ar_test()`. This test is robust to weak instruments and can be used to test hypotheses about endogenous variable coefficients. The function `ar_confint()` is also provided to compute AR confidence intervals by inverting the test.

- `etable`: arguments `extralines` and `headers` are more robust and the behavior is slightly modified. You can now position the values using integer indexes which give the columns position, inseadof column spans. It also errors more gracefully. This change is retro compatible.

- in multiple estimations in which at least one estimation contains only missing values: no error is thrown any more
Expand Down
Loading