Skip to content

error in weights when specification uses dataframe's rownames to identify units of assignment #259

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jwasserman2 merged 4 commits into from
Mar 31, 2026
Merged

error in weights when specification uses dataframe's rownames to identify units of assignment #259

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b6ed22d
BUG .join_spec_weights adds rownames as a column to allow joins for s…
jwasserman2 Mar 31, 2026
9807833
BUG fix logic
jwasserman2 Mar 31, 2026
0fcafb0
MAINT increment version
jwasserman2 Mar 31, 2026
88f8b1f
MAINT Update NEWS
jwasserman2 Mar 31, 2026
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
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
Package: propertee
Version: 1.0.4.9004
Version: 1.0.4.9005
Title: Standardization-Based Effect Estimation with Optional Prior Covariance Adjustment
Description: The Prognostic Regression Offsets with Propagation of
ERrors (for Treatment Effect Estimation) package facilitates
Expand Down
3 changes: 3 additions & 0 deletions NEWS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,6 @@
# **propertee** 1.0.5 (Unreleased)
* Fix bug in `ate()/ett()/...` when units of assignment are identified in a `StudySpecification` by the rownames of a dataframe, that is, the `StudySpecification` is created by a call of the form `*_spec(trt ~ 1 + ..., data)`

# **propertee** 1.0.4
* Fix routines for CR2/CV2 standard errors and associated degrees of freedom that previously errored when the provided `teeMod` had a non-empty `na.action`, or the `teeMod` or its `weights` argument had a `dichotomy` slot
* Return NaN for the degrees of freedom when CR2/CV2 standard errors have deficient degrees of freedom
Expand Down
3 changes: 3 additions & 0 deletions R/weights_internal.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,6 +139,9 @@ NULL
uoadata$specification_weights <- weights

# Merge with data to expand weights to unit of analysis level
if (uoanames[1L] == "..uoa.." & length(uoanames) == 1L) {
data[["..uoa.."]] <- rownames(data)
}
weights <- .merge_preserve_order(data, uoadata,
by = uoanames,
all.x = TRUE)$specification_weights
Expand Down
10 changes: 10 additions & 0 deletions tests/testthat/test.WeightedStudySpecification.notforCRAN.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -776,3 +776,13 @@ test_that("assignment weights persist when data argument excludes some units", {
expected_wts <- c(rep(2, 10), rep(1, 10), rep(0, 20))
expect_equal(wts@.Data, expected_wts)
})

test_that("weights when units of assignment are identified by rownames", {
data(simdata)
expect_warning(rct_spec <- rct_spec(z ~ 1, simdata), "explicit unit")
ettwts <- ett(rct_spec, data = simdata)
piZ <- mean(simdata$z)
expect_equal(ettwts@.Data, simdata$z + (1 - simdata$z) * piZ / (1 - piZ))
atewts <- ate(rct_spec, data = simdata)
expect_equal(atewts@.Data, simdata$z / piZ + (1 - simdata$z) / (1 - piZ))
})
Loading