v0.3.2

• Swapped internal use of dplyr::case_when() for dplyr::recode_values() as the former is now deprecated. (#327)

Full Changelog: v0.3.1...v0.3.2

v0.3.1

• Added the ard_emmeans_emmeans() function. (#317)
• Renamed ard_emmeans_mean_difference() to ard_emmeans_contrast() to align with function naming conventions.
• The ard_complex() function has been renamed to ard_mvsummary().

What's Changed

• draft for mean.estimates included in mean.difference.estimates (ANCOVA in tern) by @ayogasekaram in #265
• Split ard_emmeans_mean_difference() function into ard_emmeans_contrast() and ard_emmeans_emmeans() by @edelarua in #318
• Use skip_if_pkg_not_installed() by @edelarua in #321
• Add insightsengineering/crane to .revdeprefs.yaml by @shajoezhu in #323
• Add coda package dependency by @shajoezhu in #324
• Update DESCRIPTION: deps update by @ddsjoberg in #325

Full Changelog: v0.3.0...v0.3.1

v0.3.0

New Features and Updates

• Added function ard_tabulate_abnormal() to calculate ARDs for abnormality analyses. (#310)
• Adding strata argument to ard_tabulate_max(). (#445, @jtalboys)
• Added function ard_incidence_rate() to calculate ARDs for incidence rate estimation. (#234)

Lifecycle Changes

• The following functions have been renamed.

  • ard_continuous() to ard_summary()
  • ard_categorical() to ard_tabulate()
  • ard_dichotomous() to ard_tabulate_value()
  • ard_categorical_max() to ard_tabulate_max()

• Updating any fmt_fn references to fmt_fun for consistency.

  • Any function with an argument cardx::foo(fmt_fn) has been updated to cardx::foo(fmt_fun). The old syntax will continue to function, but with a deprecation warning to users.
  • Importantly, the ARD column named "fmt_fn" has been updated to "fmt_fun". This change cannot be formally deprecated. For users who were accessing the ARD object directly to modify this column instead of using functions like cards::update_ard_fmt_fun(), this will be a breaking change.

Bug Fixes

• Fix in ard_survival_survfit.data.frame() method where the stratifying variable was not correctly converted back to its original type.
• Fix in ard_total_n.survey.design() to use update() instead of dplyr::mutate(), which sometimes caused a downstream issue.

What's Changed

• Add ard_abnormal() for abnormality calculations by @edelarua in #311
• Surface deff argument and set default to FALSE by @malcolmbarrett in #313
• Core function renames by @ddsjoberg in #315

New Contributors

• @malcolmbarrett made their first contribution in #313

Full Changelog: v0.2.5...v0.3.0

v0.2.5

• Adding strata argument to ard_categorical_max(). (#445, @jtalboys)

• Added function ard_incidence_rate() to calculate ARDs for incidence rate estimation. (#234)

• Updating any fmt_fn references to fmt_fun for consistency.

  • Any function with an argument cardx::foo(fmt_fn) has been updated to cardx::foo(fmt_fun). The old syntax will continue to function, but with a deprecation warning to users.
  • Importantly, the ARD column named "fmt_fn" has been updated to "fmt_fun". This change cannot be formally deprecated. For users who were accessing the ARD object directly to modify this column instead of using functions like cards::update_ard_fmt_fun(), this will be a breaking change.

• Fix in ard_survival_survfit.data.frame() method where the stratifying variable was not correctly converted back to its original type.

• Fix in ard_total_n.survey.design() to use update() instead of dplyr::mutate(), which sometimes caused a downstream issue.

What's Changed

• Add ard_incidence_rate() by @edelarua in #280
• update forcats standalone script by @ayogasekaram in #297
• Fix in ard_survival_survfit.data.frame() type conversion by @ddsjoberg in #298
• Add strata argument to ard_categorical_max by @jtalboys in #300
• Fmt fn to fmt fun by @ddsjoberg in #302
• 267 add unit test@main by @ayogasekaram in #293

New Contributors

• @jtalboys made their first contribution in #300

Full Changelog: v0.2.4...v0.2.5

v0.2.4

New Features and Updates

• Added function ard_stats_mantelhaen_test() to calculate ARDs for Cochran-Mantel-Haenszel test results using stats::mantelhaen.test(). (#238)
• Added a ard_regression.data.frame() S3 method. Also converted ard_regression_basic() to an S3 generic and added a ard_regression_basic.data.frame() method (#287)
• Specifying ard_survfit_survfit.data.frame(variables=NULL) now creates an unstratified survfit() model, where previously variables argument could not be empty. (#277)
• The ard_survfit_survfit.data.frame(variables) now accepts tidyselect input. (#278)
• Added conf.level and conf.type to ard_survival_survfit() results. (#218)
• Added cards::as_cards_fun() to ard_emmeans_mean_difference() so when an error occurs the user gets an ARD with the expected ARD structure. (#132)

What's Changed

• Add parameter checks to ard_survival_survfit() by @edelarua in #276
• pull changes from standalone script by @ayogasekaram in #273
• ard_survfit_survfit.data.frame() can now construct unstratified model by @ddsjoberg in #279
• Adding ard_regression.data.frame() method by @ddsjoberg in #288
• Add conf.level to ard_survival_survfit() results by @edelarua in #282
• Capture errors from ard_emmeans_mean_difference() using as_cards_fn() by @edelarua in #283
• Add ard_stats_mantelhaen_test() by @edelarua in #246
• Returning ard_survival_survfit() conf.level as numeric (was previously character) by @ddsjoberg in #291

Full Changelog: v0.2.3...v0.2.4

v0.2.3

New Features and Updates

• Added function ard_categorical_max() to calculate categorical occurrence rates by maximum level per unique ID. (#240)

Other Updates

• Little n is now returned with the results of the proportion_ci_*() functions, which then flows into the results of ard_proportion_ci(). (#256)
• Added as_cards_fun() to ard_categorical_ci() so when there is an error, the user gets an ARD with the expected ARD structure. (#262)
• Update in ard_categorical.survey.design() for factor variables that are all missing. These variables can now be tabulated, where previously this resulted in an error.
• Update in ard_missing.survey.design() where we can now tabulate the missing rate of design variables, such as the weights.

Bug Fixes

• Fixed a bug in ard_survival_survfit() causing an error when "=" character is present in stratification variable level labels. (#252)
• Bug fix in ard_categorical_ci(denominator='cell') when missing values were present in the by variable.

What's Changed

• update for fct variables that are all NA by @ddsjoberg in #248
• Replace logo.png by logo.svg by @llrs-roche in #249
• Fix in ard_missing() for design variables by @ddsjoberg in #250
• Adding ard_categorical_ci(denominator) argument by @ddsjoberg in #251
• Revert to png logo by @llrs-roche in #254
• cleaning up by @ddsjoberg in #255
• Fix bug in ard_survival_survfit() when "=" is in strata variable labels by @edelarua in #253
• Add ard_categorical_max() by @edelarua in #244
• Fix failing integration test by @edelarua in #258
• Removed spelling from DESCRIPTION, similar to what was done in cards by @kimjj93 in #259
• Adding n to the proportion_ci*() results by @ddsjoberg in #260
• Adding as_cards_fun() to ard_categorical_ci() by @ddsjoberg in #263
• better handling of NA values in ard_categorical_ci() by @ddsjoberg in #266
• Increase cards min version req by @ddsjoberg in #268
• release prep by @ddsjoberg in #271
• Remove lookup-refs by @m7pr in #264

New Contributors

• @llrs-roche made their first contribution in #249
• @kimjj93 made their first contribution in #259
• @m7pr made their first contribution in #264

Full Changelog: v0.2.2...v0.2.3

v0.2.2

• Added a data.frame method to ard_survival_survfit().
• Added a warning for incorrect formula type to ard_survival_survfit(). (#223)
• Implemented summary(extend=TRUE) in ard_survival_survfit() to return results for time points out of bounds. (#224)
• Methods in the {survey} and {survival} packages do not retain inputs variables types in their outputs. We now are able retain these variable types in ARDs returned by ard_continuous.survey.design(), ard_categorical.survey.design(), ard_continuous_ci.survey.design(), ard_categorical_ci.survey.design(), and ard_survival_survfit.data.frame() (and notably, not in ard_survival_survfit.survfit()).

What's Changed

• Update DESCRIPTION by @ddsjoberg in #209
• Workflow propagations by @walkowif in #206
• align lme4 version with current rspm version by @shajoezhu in #211
• adding example specifying conf level in ard_survival_survfit() by @ddsjoberg in #217
• update tests by @ayogasekaram in #220
• 213 update standalone@main by @ayogasekaram in #225
• Enhance formula processing in ard_survival_survfit() by @edelarua in #226
• Update check.yaml by @shajoezhu in #230
• add ard_categorical_ci.data.frame tests. by @ayogasekaram in #228
• Update scheduled.yaml by @pawelru in #232
• Added function to restore types in ARDs by @ddsjoberg in #231

New Contributors

• @shajoezhu made their first contribution in #211
• @pawelru made their first contribution in #232

Full Changelog: v0.2.1...v0.2.2

v0.2.1

New Features and Updates

• Added S3 method ard_total_n.survey.design() which returns an ARD with both the survey-weighted and unweighted total sample size.
• Added warning and error columns to ard_regression() output. (#148)
• Implemented cards::as_card() where needed in the package to convert data frames to class 'card'. (#200)

Bug Fixes

• Bug fix in ard_categorical.survey.design() where all unweighted statistics were returned, even in the case where they were explicitly not requested.

Lifecycle Changes

• The bt(pattern), reformulate2(pattern_term), reformulate2(pattern_response) arguments have been deprecated and are now ignored. We now use make.names() to determine whether a column name needs to be wrapped in backticks. (#192)

What's Changed

• Workflow propagations by @walkowif in #191
• Add website URL to DESCRIPTION by @edelarua in #190
• Update pkgdown site logo by @edelarua in #196
• Adding ard_total_n.survey.design() S3 method by @ddsjoberg in #199
• Add warning and error columns to ard_regression() output by @edelarua in #195
• Implement cards::as_card() by @edelarua in #201
• add check_ard_structure() unit tests by @ayogasekaram in #197
• Add ard_*() function for stats::poisson.test() by @edelarua in #194
• bt(pattern) update by @ddsjoberg in #207

Full Changelog: v0.2.0...v0.2.1

v0.2.0

Breaking Changes

• Updated function names to follow the pattern ard_<pkgname>_<fnname>(). This change is immediate: previous functions names have not been deprecated. (#106)

ard_ttest()             -> ard_stats_t_test()
ard_paired_ttest()      -> ard_stats_paired_t_test()
ard_wilcoxtest()        -> ard_stats_wilcox_test()
ard_paired_wilcoxtest() -> ard_stats_paired_wilcox_test()
ard_chisqtest()         -> ard_stats_chisq_test()
ard_fishertest()        -> ard_stats_fisher_test()
ard_kruskaltest()       -> ard_stats_kruskal_test()
ard_mcnemartest()       -> ard_stats_mcnemar_test()
ard_moodtest()          -> ard_stats_mood_test()

New Features

• The ard_categorical_ci(value) argument has been added. Previously, only binary variables (0/1 or TRUE/FALSE) could be summarized. When a value is not supplied, each level of the variable is summarized independently. By default, binary variables will have the 1/TRUE level summarized.
• Added the following functions for calculating Analysis Results Datasets (ARDs).
  • ard_stats_aov() for calculating ANOVA results using stats::aov(). (#3)
  • ard_stats_anova() for calculating ANOVA results using stats::anova(). (#12)
  • ard_stats_mcnemar_test_long() for McNemar's test from long data using stats::mcnemar.test().
  • ard_stats_prop_test() for tests of proportions using stats::prop.test(). (#64)
  • ard_stats_t_test_onesample() for calculating one-sample results.
  • ard_stats_wilcox_test_onesample() for calculating one-sample results.
  • ard_stats_oneway_test() for calculating ANOVA results using stats::oneway.test(). (#3)
  • ard_aod_wald_test() for calculating Wald Tests for regression models using aod::wald.test(). (#84)
  • ard_car_anova() for calculating ANOVA results using car::Anova(). (#3)
  • ard_car_vif() for calculating the variance inflation factor using car::vif(). (#10)
  • ard_effectsize_cohens_d(), ard_effectsize_paired_cohens_d(), ard_effectsize_hedges_g(), and ard_effectsize_paired_hedges_g() for standardized differences using effectsize::cohens_d() and effectsize::hedges_g(). (#50)
  • ard_emmeans_mean_difference() for calculating the least-squares mean differences using the {emmeans} package. (#34)
  • ard_smd_smd() for calculating standardized mean differences using smd::smd(). (#4)
  • ard_survival_survfit() for survival analyses using survival::survfit(). (#43)
  • ard_continuous.survey.design() for calculating univariate summary statistics from weighted/survey data using many functions from the {survey} package. (#68)
  • ard_categorical.survey.design() for tabulating summary statistics from weighted/survey data using many functions from the {survey} package. (#140)
  • ard_dichotomous.survey.design() for tabulating dichotomous summary statistics from weighted/survey data using many functions from the {survey} package. (#2)
  • ard_missing.survey.design() for tabulating missing summary statistics from weighted/survey data using many functions from the {survey} package. (#2)
  • ard_attributes.survey.design() for summarizing labels and attributes from weighted/survey data using many functions from the {survey} package.
  • ard_survey_svychisq() for weighted/survey chi-squared test using survey::svychisq(). (#72)
  • ard_survey_svyttest() for weighted/survey t-tests using survey::svyttest(). (#70)
  • ard_survey_svyranktest() for weighted/survey rank tests using survey::svyranktest(). (#71)
  • ard_survival_survdiff() for creating results from survival::survdiff(). (#113)
  • ard_regression_basic() for basic regression models. The function focuses on matching model terms to underlying variables names. (#46)
• Updated functions ard_stats_t_test(), ard_stats_paired_t_test(), ard_stats_wilcox_test(), ard_stats_paired_wilcox_test(), ard_stats_chisq_test(), ard_stats_fisher_test(), ard_stats_kruskal_test(), ard_stats_mcnemar_test(), and ard_stats_mood_test() to accept multiple variables at once. Independent tests are calculated for each variable. The variable argument is renamed to variables. (#77)
• Updated ard_stats_t_test() and ard_stats_wilcox_test() to no longer require the by argument, which yields central estimates with their confidence intervals. (#82)
• Added model construction helpers, construct_model(), reformulate2(), bt(), and bt_strip().
• Imported cli call environment functions from https://github.com/ddsjoberg/standalone/blob/main/R/standalone-cli_call_env.R and implemented set_cli_abort_call in user-facing functions. (#111)

What's Changed

• Initial setup by @ddsjoberg in #8
• Adding t-test ARDs by @ddsjoberg in #16
• Small pkg prep by @ddsjoberg in #17
• Small pkg prep by @ddsjoberg in #18
• Adding Wilcoxon Rank-Sum Tests by @ddsjoberg in #25
• Adding ard_chisqtest() by @ddsjoberg in #22
• adding ard_fishertest() by @ddsjoberg in #21
• adding proportion CIs by @ddsjoberg in #9
• Adding ard_regression() by @ddsjoberg in #26
• Closes #38 adding Kruskal-Wallis test by @zdz2101 in #45
• {cards} arg rename updates by @ddsjoberg in #53
• Pkgdown workflow test by @ddsjoberg in #55
• McNemar's statistical test addition: ard_mcnemartest by @Melkiades in #51
• Closes #52 for moods test by @zdz2101 in #52
• general renaming by @ddsjoberg in #58
• Updating checks file by @ddsjoberg in #60
• Adds ard_regression_basic(). by @rparmm in #62
• Cohen's D and Hedge's G ARD Functions by @ayogasekaram in #57
• Adding ard_proptest() by @ddsjoberg in #64
• Adding ard_smd() by @ddsjoberg in #65
• Adding ard_car_anova() by @ddsjoberg in #67
• Closes #49 add formulas/document the methods of CI interval calculation in LaTeX by @zdz2101 in #63
• Closes #10 add ard_vif() by @zdz2101 in #61
• Updated ard_wilcoxtest() to allow multiple variables by @ddsjoberg in #81
• update ard_cohens_d function to accept multiple variables by @ayogasekaram in #87
• update ard_hedges_g and ard_paired_hedges_g by @ayogasekaram in #88
• update ard_moodtest function to accept multiple variables by @ayogasekaram in #90
• add ard_svychisq() function by @ayogasekaram in #83
• Updated ard_ttest() to accept multiple variables. by @ddsjoberg in #79
• adding ard_svyttest() by @ddsjoberg in #75
• Adding ard_svycontinuous() for weighted continuous variable summaries by @ddsjoberg in #69
• ard_smd() for weighted data by @ddsjoberg in #74
• update ard_chisqtest to accept multiple vars. by @ayogasekaram in #93
• update ard_fischertest() to accept multiple vars by @ayogasekaram in #94
• update ard_mcnemartest() and ard_kruskaltest() by @ayogasekaram in #96
• update ard_proptest() and ard_smd() by @ayogasekaram in #98
• Closes #15 adds CI for univariate/single statistics by @zdz2101 in #82
• fix bugs with cohens_d/hedges_g by @zdz2101 in #102
• Closes #71 ard for svyranktest by @zdz2101 in #100
• Add ARD function for survfit objects by @edelarua in #59
• add ard_aov and ard_onewaytest by @ayogasekaram in #44
• rename functions with new package conventions. by @ayogasekaram in #110
• add ard_aod_wald_test function by @ayogasekaram in #99
• Adding ard_stats_anova() by @ddsjoberg in #107
• Use cli call env functions by @edelarua in #112
• Add @examplesIf to internal examples where applicable by @edelarua in #120
• update context after renaming ard_* functions by @ayogasekaram in #123
• reorganize pkgdown by @ayogasekaram in #122
• Adding ard_survival_survdiff() by @ddsjoberg in #119
• Bumping broom.helpers required version to 1.15...

cardx 0.1.0

• Initial release.