Changelog
Source:NEWS.md
DeclareDesign 1.1.1
CRAN release: 2026-04-28
- Bug fix: replaced unexported rlang internal
quo_get_env()with the exportedget_env()inaaa.Randdeclare_potential_outcomes.R. The unexported function caused test failures on CRAN when rlang updated its export list. - Bug fix: replaced
enquo()withsubstitute()in+.ddto correctly capture step expressions under the new rlang C API. Thanks to Lionel Henry (@lionel-) for the fix. - Added
CausalQueries,rdrobust, andrdsstoSuggeststo satisfy CRAN dependency checks for tests that use those packages. - Made top-level test setup use soft package loads so checks pass when suggested packages are not locally installed.
- Improved
print.design()output: clearer labels, deduplication of parameter names across environments, and truncation of long values in the printed parameter table. - Added example to
select_diagnosands()documentation showing use of thealphaargument.
DeclareDesign 1.1.0
CRAN release: 2025-10-15
- Added global variable capture for design steps to improve serialization and portability of declared designs.
- Swapped margins for marginaleffects.
- Changes to tests and examples to not depend on suggested packages.
DeclareDesign 1.0.10
CRAN release: 2024-04-21
- Swapped margins for marginaleffects.
- Changes to tests and examples to not depend on suggested packages.
DeclareDesign 1.0.8
CRAN release: 2024-03-07
- Bug fix of parallel processing that caused in rare cases simulations to be identical across multiple calls to simulate_design or diagnose_design.
DeclareDesign 1.0.0
CRAN release: 2022-06-20
- Allow diagnoses to group by outcomes.
- Simplify print(design).
- Launch version 1.
DeclareDesign 0.30.0
CRAN release: 2022-01-28
- New tidy(diagnosis) function to construct a tidy data frame of diagnosand estimates and summary statistics including bootstrapped standard error and confidence intervals.
- Remove draw_assignment and draw_sample function.
- Added diagnosis duration to summary function.
- Bug fixes.
DeclareDesign 0.28.0
CRAN release: 2021-08-21
- To simplify output of diagnoses, we changed the names of the variables from design_label to design, inquiry_label to inquiry, and estimator_label to estimator.
- declare_assignment() and declare_sampling() have the default values for legacy set to FALSE. You can still use the legacy versions of these functions by manually setting legacy = TRUE for some time, but this functionality will later be removed.
DeclareDesign 0.26.0
CRAN release: 2021-02-14
- Rapid development phase is beginning to prepare for DeclareDesign 1.0.
- Add new step
declare_modelfor defining the model of the world including sample size, levels of the data, and variables. - Add new step
declare_inquiryto replacedeclare_estimand.declare_estimandis still available but deprecated. - Soft-introduce new syntax for declare_assignment and declare_sampling. Old syntax is still available with legacy = TRUE, the current default. To use the new syntax, set legacy = FALSE. In future versions of DeclareDesign, the default will be set to FALSE.
-
reveal_outcomes, created in 0.24.0, has been removed as a step. - Change labels produced in diagnoses and
run_designoutput to beinquiry_labelrather thanestimand_label. - Allow estimands to be functions of other estimands.
DeclareDesign 0.24.0
CRAN release: 2020-11-14
- Add new step
declare_measurementfor measuring outcome variables. - Add
declare_testto enable hypothesis testing where no estimand is targeted. For example,declare_testcould be used for a K-S test of distributional equality anddeclare_estimatorfor a difference-in-means estimate of an average treatment effect. - Add
model_summaryoption todeclare_estimator, to enable specifying a model and then a separate post-estimation function to extract coefficient estimates (e.g., estimate of a treatment effect) or model summary statistics (e.g., R^2 or the result of an F-test from a regression). - Simplify
declare_diagnosandsfunctionality.diagnose_design()by default runs an internal function with a set of default diagnosands, including power, RMSE, bias, type S rate, coverage, mean estimate, and mean estimand. - Improve compatibility with dplyr verbs as handlers.
filternow works. - Rename
declare_revealtoreveal_outcomes. Both continue to work.
DeclareDesign 0.22.0
CRAN release: 2020-03-24
- Fix ability to set
sampling_variableindeclare_sampling. - Add ability to retain nonsampled data after sampling via
drop_nonsampledflag indeclare_sampling.
DeclareDesign 0.20.0
CRAN release: 2019-09-10
- Add
compare_diagnosesfunction to compare two designs on the basis of their design diagnoses. - Compatibility with
rlang0.4.0 - Bug fixes
DeclareDesign 0.18.0
CRAN release: 2019-04-30
- Add
compare_designsfunctions to compare the code and output of designs side-by-side. - Bug fixes
DeclareDesign 0.16.0
CRAN release: 2019-01-26
- Add
draw_assignmentfunction to draw an assignment vector(s) given data - Add
draw_samplefunction to draw a sample or multiple sequential samples from data - Rewrite
draw_datato optionally take a data argument.draw_datanow can be used to draw data for the full design, or for subsets of it.startandendflags are added to select which portions of the design to run - Bug fixes
DeclareDesign 0.12.0
CRAN release: 2018-11-09
- Add ability to use
get_estimateswith data, useful for example for getting estimates after data is collected for a study. To draw estimates or estimands from simulated data, now use renameddraw_estimatesanddraw_estimandsfunctions. - Documentation improvements
- Bug fixes