tabulate_rsp_subgroups() and
tabulate_survival_subgroups() to specify parameter
parent_name when using split_rows_by() and
analyze() internally to enhance table paths.g_lineplot() where
table_format and table_labels arguments were
ignored.g_lineplot() to allow use of a function as
a format for table stats.assert_df_with_factors(),
assert_df_with_variables(),
assert_proportion_value(),
check_diff_prop_ci(), clogit_with_tryCatch(),
get_covariates(), labels_or_names(),
range_noinf() , s_surv_timepoint(), and
s_test_proportion_diff() to exported functions.count_abnormal(),
count_abnormal_by_baseline(),
count_abnormal_by_marked(),
count_abnormal_by_worst_grade(),
count_abnormal_lab_worsen_by_baseline(),
count_cumulative(), count_missed_doses(),
coxph_pairwise(), estimate_multinomial_rsp(),
estimate_proportion(),
estimate_proportion_diff(),
estimate_odds_ratio(), summarize_ancova(),
summarize_glm_count(),
summarize_num_patients(), surv_timepoint(),
and test_proportion_diff() to work without
make_afun().afun_riskdiff(),
count_occurrences(),
count_occurrences_by_grade(),
count_patients_with_event(),
count_patients_with_flags(), count_values(),
estimate_incidence_rate(),
h_tab_one_biomarker(), summarize_change(),
summarize_colvars(),
summarize_patients_exposure_in_cols(),
survival_time(), tabulate_rsp_subgroups(),
tabulate_survival_subgroups(),
tabulate_rsp_biomarkers(), and
tabulate_survival_biomarkers() to align with new analysis
function style.geom_sd and geom_mean_sd to
s_summary() as default available statistics.denom parameter to
estimate_proportion().weights_emmeans argument to
summarize_ancova().a_count_patients_with_flags() preventing
select custom label/indentation formats from being applied.tabulate_rsp_subgroups() and
tabulate_survival_subgroups() preventing the
pct option from having an effect when adding a risk
difference column..stats when adding custom
statistical functions.table_names argument to
count_abnormal_lab_worsen_by_baseline().h_split_param()
function.label_all parameter to
tabulate_rsp_subgroups(), with redirection to the same
parameter in extract_rsp_subgroups().h_tab_one_biomarker(),
h_tab_rsp_one_biomarker(), and
h_tab_surv_one_biomarker().make_afun().geom_mean statistical output.h_tab_rsp_one_biomarker() and
h_tab_surv_one_biomarker() into
h_biomarkers_subgroups.R.utils_factor.R) into a single file.as_factor_keep_attributes() to an exported
function.ungroup_stats() and replaced
its usage with the get_*_from_stats() functions.s_count_nonmissing() as it is a non-repeated
small and internal function.denom parameter to
s_count_cumulative(), s_count_missed_doses(),
and s_count_occurrences_by_grade()."N_row" as an optional input to
denom in s_count_occurrences().rel_height_plot parameter to
g_lineplot() to control the line plot height relative to
annotation table height.as_list parameter to g_lineplot() to
allow users to return the line plot and annotation table elements as a
list instead of stacked for more complex customization.tern functions” for
future reference.analyze_vars() statistical names that are used
by rtables::as_result_df().analyze_vars().analyze_vars() and a_summary()
to take all options from
?rtables::additional_fun_params.summarize_change() and
count_values() to work without
make_afun().a_count_occurrences_by_grade(),
a_count_patients_with_event(), and
a_count_patients_with_flags() to no longer use
make_afun().get_labels_from_stats() to use a named list
of levels for each statistic instead of row names.table_font_size parameter of
g_lineplot() to control the size of all text in the
annotation table, including labels.compare_vars() into analyze_vars()
as overlap was significant.a_summary() causing non-unique
row_name values to occur when multiple statistics are
selected for count variables.summary_formats() and summary_labels(). Added
disclaimer about underlying use of get_stats.NA for
summarize_change().count_fraction_fixed_dp exception by assigning
it to the result of count_fraction with a different format
output.median_ci_3d to s_summary which
includes estimate and confidence interval in one statistic.median_ci_3d, quantiles_lower and
quantiles_upper to s_surv_time which includes
estimate and confidence interval in one statistic.hr_ci_3d to s_coxph_pairwise which
includes estimate and confidence interval in one statistic.event_free_rate_3d to
s_surv_timepoint which includes estimate and confidence
interval in one statistic.rate_diff_ci_3d to
s_surv_timepoint_diff which includes estimate and
confidence interval in one statistic.errorbar_width and linetype
parameters to g_lineplot..formats argument to
tabulate_rsp_subgroups and
tabulate_survival_subgroups to allow users to specify
formats.riskdiff argument to
tabulate_rsp_subgroups and
tabulate_survival_subgroups to allow users to add a risk
difference table column, and function control_riskdiff to
specify settings for the risk difference column.tabulate_rsp_subgroups when
pval statistic is selected but df has not been
correctly generated to add p-values to the output table.n_rate statistic as a non-default option to
estimate_incidence_rate which returns both number of events
observed and estimated incidence rate.n_unique statistic as a non-default option to
estimate_incidence_rate which returns total number of
patients with at least one event observed.estimate_incidence_rate to work as both an
analyze function and a summarize function, controlled by the added
summarize parameter. When summarize = TRUE,
labels can be fine-tuned via the new label_fmt argument to
the same function.fraction statistic to the
analyze_var_count method group.summarize_glm_count() documentation and all
its associated functions to better describe the results and the
functions’ purpose.method argument to s_odds_ratio()
and estimate_odds_ratio() to control whether exact or
approximate conditional likelihood calculations are used.d_count_cumulative parameters as
described in the documentation.g_lineplot x-axis were
not shown in either plots.a_surv_time that threw an error when
split only has "is_event".g_lineplot when using only
one group or strata level.get_formats_from_stats and
get_labels_from_stats.scale parameter)
being applied to response but not to rate in h_glm_count
while all distributions have logarithmic link function.decorate_grob that did not handle well
empty strings or NULL values for title and footers.g_km that caused an error when multiple
records in the data had estimates at max time.\n and
vector behavior that did not cope well with
split_string().summary_formats and summary_labels.strata and
cohort_id arguments to g_lineplot.h_incidence_rate.R file.facet_var to g_lineplot to allow
plot faceting by a factor variable.label_all parameter to
extract_survival_biomarkers and
extract_survival_subgroups.xticks, xlim, and
ylim arguments to g_lineplot to allow for
customization of the x and y axes.g_lineplot legend to follow factor levels set
by users.s_ancova that prevented statistics from
being printed when arm levels include special characters.decorate_grob that prevented the right
margins to be respected when adding title and footers decorations.label_all parameter to
tabulate_survival_biomarkers and
tabulate_survival_subgroups, with redirection to the same
parameter in their associated extract_* functions.h_glm_negbin to h_glm_count to
enable count data analysis using a negative binomial model.grade_groups_only to
count_occurrences_by_grade to allow users to only display
rows for specified grade groups.df2gg that converts
data.frame objects to ggplot objects.control_surv_med_annot and
control_coxph_annot to configure g_km
annotation table sizes/positions.g_km to output a ggplot object
instead of a grob object.g_forest to output a ggplot
object instead of a grob object.mean_pval) updated
from "xx.xx" to "x.xxxx | (<0.0001)".rtable2gg to clean up appearance of text labels.s_ancova causing incorrect difference
calculations for arm variables with irregular levels.format_count_fraction_fixed_dp that did
not have the same print when the fraction was 1 (100%).g_lineplot causing default labels not to
update according to specified control settings.NA values.expect_snapshot_ggplot to test setup
file to process plot snapshot tests and allow plot dimensions to be
set.ggplot2
3.5.0.individual_patient_plot.R to
g_ipp.R.time_unit_input, time_unit_output,
na_level and indent_mod.summarize_vars,
control_summarize_vars, a_compare,
create_afun_summary, create_afun_compare, and
summary_custom.vdiffr package from Suggests in DESCRIPTION
file.strat, to be
renamed to strata, within the variables
argument to h_rsp_to_logistic_variables,
h_logistic_mult_cont_df,
h_odds_ratio_subgroups_df,
h_coxreg_mult_cont_df, h_coxph_subgroups_df,
h_tbl_coxph_pairwise, extract_rsp_biomarkers,
extract_rsp_subgroups,
extract_survival_biomarkers, and
extract_survival_subgroups.strat argument to
s_coxph_pairwise and replaced it with the
strata argument.forest_grob,
forest_dot_line, forest_viewport,
vp_forest_table_part, and grid.forest
functions.h_ggkm, h_decompose_gg,
h_km_layout, h_grob_tbl_at_risk,
h_grob_median_surv, h_grob_y_annot, and
h_grob_coxph.grob/grid related
functions stack_grobs, arrange_grobs, and
draw_grob which are no longer used in
tern.ref_group_position function to place the
reference group facet last, first or at a certain position.keep_level_order split function to retain
original order of levels in a split.level_order split function to reorder manually
the levels.get_indents_from_stats to format and
return indent modifiers for a given set of statistics.apply_auto_formatting
to check for "auto" formats and replace them with
implementation of format_auto in analyze functions.labels_use_control to modify
labels with control specifications.tern_default_stats.count_occurrences
analyze function, summarize_occurrences.surv_time for censored
range observations, controlled via the ref_fn_censor
parameter.h_adlb_abnormal_by_worst_grade to
prepare ADLB data to use as input in
count_abnormal_by_worst_grade.s_bland_altman function to assess agreement
between two numerical vectors.rtable2gg that converts
rtable objects to ggplot objects.na_str globally
with set_default_na_str() and added
default_na_str() for all interested functions.ref_group_coxph parameter to g_km to
specify the reference group used for pairwise Cox-PH calculations when
annot_coxph = TRUE.annot_coxph_ref_lbls parameter to
g_km to enable printing the reference group in table labels
when annot_coxph = TRUE.x_lab parameter to g_lineplot to
customize x-axis label.g_lineplot.arm_y argument.count_by input in
analyze_num_patients and
summarize_num_patients.g_lineplot.decorate_grob preventing text wrapping
from accounting for font size.na_str argument in all
column-wise analysis and tabulation functions.to_string_matrix to take into account
widths and other printing parameters.na_str argument to analyze &
summarize_row_groups wrapper functions
count_abnormal, count_abnormal_by_baseline,
count_abnormal_by_marked,
count_abnormal_by_worst_grade,
count_abnormal_lab_worsen_by_baseline,
count_cumulative, count_missed_doses,
count_occurrences, count_occurrences_by_grade,
summarize_occurrences_by_grade,
summarize_patients_events_in_cols,
count_patients_with_event,
count_patients_with_flags, count_values,
estimate_multinomial_response,
estimate_proportion, h_tab_one_biomarker,
estimate_incidence_rate,
logistic_summary_by_flag, estimate_odds_ratio,
estimate_proportion_diff,
test_proportion_diff, summarize_ancova,
summarize_change, summarize_glm_count,
summarize_num_patients, analyze_num_patients,
summarize_patients_exposure_in_cols,
coxph_pairwise, tabulate_survival_subgroups,
surv_time, and surv_timepoint.format_count_fraction_lt10
for formatting count_fraction with special consideration
when count is less than 10.s_summary.logical output for
count_fraction when denominator is zero to display as
NA instead of 0 in tables.analyze_vars_in_cols to allow character input
to indicate whether nominal time point is post-dose or pre-dose when
applying the 1/3 imputation rule.g_km causing an error when converting
certain annotation width units.na_level argument in
s_count_abnormal_by_baseline, a_summary,
analyze_vars, analyze_vars_in_cols,
compare_vars, h_map_for_count_abnormal,
h_stack_by_baskets, summarize_colvars,
a_coxreg, and summarize_coxreg and replaced it
with the na_str argument.strata and cohort_id parameters renamed to
group_var and subject_var respectively in
g_lineplot and control_lineplot_vars .imputation_rule function to apply imputation rule
to data.format_sigfig to allow for
numeric value formatting by a specified number of significant
figures.tern_default_formats and tern_default_labels,
respectively.get_stats to return methods from given
statistical method groups.get_formats_from_stats to return formats
and get_labels_from_stats to return labels for a given set
of statistics."auto" option for .formats. It uses
format_auto to determine automatically the number of
digits.title argument to h_grob_tbl_at_risk
and annot_at_risk_title argument to g_km and
h_km_layout which allows user to add “Patients at Risk”
title to Kaplan-Meier at risk annotation table.tabulate_rsp_subgroups to pass sanitation
checks by preventing creation of degenerate subtables.analyze_vars_in_cols to use caching, allow
implementation of imputation rule via the imp_rule
argument, and allow user to specify cell alignment via the
.aligns argument.add_rowcounts to allow addition of row counts
from alt_counts_df using the alt_counts
argument.gp argument to g_forest to control
graphical parameters such as font size.utils_defaults_handling.R.summary_custom() and
a_summary() as a S3 method.p-value in the discrete
case to pval_counts.a_summary_internal() in favor of only one main
a_summary().stat_propdiff_ci function to calculate
proportion/risk difference and CI.riskdiff argument to functions
count_occurrences, count_occurrences_by_grade,
count_patients_with_event,
count_patients_with_flags,
analyze_num_patients, and
summarize_num_patients.a_summary to no longer use the
helper function create_afun_summary.summarize_vars and
compare_vars to use the refactored a_summary
function.ungroup_stats to
ungroup statistics calculated for factor variables, and
a_summary_internal to perform calculations for
a_summary.s_count_occurrences_by_grade so that
“missing” grade always appears as the final level.analyze_vars_in_cols when categorical data
was used.s_count_occurrences_by_grade so that
levels are not relabeled when reordering to account for “missing”
grades..N_row and
.N_col parameters.df_explicit_na. Changes in
NA values should happen externally to tern
functions, depending on users’ needs.create_afun_summary and
create_afun_compare.ylim argument to g_km to allow the
user to set custom limits for the y-axis.g_km which checks whether there is
one arm present in the data when annot_coxph is true.flag_labels argument to
s_count_patients_with_flags to enable more label handling
options in count_patients_by_flags.nested argument to analyze
wrapper functions count_abnormal,
count_abnormal_by_baseline,
count_abnormal_by_marked,
count_abnormal_by_worst_grade,
count_abnormal_lab_worsen_by_baseline,
count_cumulative, count_missed_doses,
count_occurrences, count_occurrences_by_grade,
count_patients_with_event,
count_patients_with_flags, count_values,
estimate_multinomial_response,
estimate_proportion, estimate_incidence_rate,
estimate_odds_ratio, estimate_proportion_diff,
test_proportion_diff, summarize_ancova,
summarize_change, summarize_glm_count,
analyze_num_patients, coxph_pairwise,
surv_time, and surv_timepoint.summarize_vars and
control_summarize_vars. Renamed into
analyze_vars and control_analyze_vars to
reflect underlying rtables machinery while keeping backward
compatibility with aliases.character class to
h_coxreg_inter_effect enabling character
covariates in summarize_coxreg.time_unit_input and
time_unit_output arguments and replaced them with the
input_time_unit and num_pt_year, respectively,
in control_incidence_rate.pairwise function.a_compare and replaced it with
a_summary with argument compare = TRUE.create_afun_summary and
create_afun_compare which are no longer used by
a_summary and a_compare respectively.sum(weights) for
M1mac installation.g_km plot “at risk”
annotation tables.analyze_patients_exposure_in_cols..indent_mods argument in functions
h_tab_one_biomarker, h_tab_rsp_one_biomarker,
h_tab_surv_one_biomarker, summarize_logistic,
logistic_summary_by_flag,
tabulate_rsp_biomarkers, a_coxreg,
summarize_coxreg,
tabulate_survival_biomarkers, surv_time,
surv_timepoint, and cfun_by_flag.summarize_coxreg to print covariates in data
rows for univariate Cox regression with no interactions and content rows
otherwise.d_count_abnormal_by_baseline labels.g_km
and added dynamic scaling of the surv_med and
coxph annotation tables, with customization via the
width_annots argument.split_text_grob preventing titles and
footnotes from being properly formatted and printed by
decorate_grob.g_lineplot preventing the addition of
lines to the plot when midpoint statistic calculations result in
NA value(s).tern:::tidy.glm formals to respect
broom:::tidy.default formals.README to include installation instructions for
CRAN.has_count_in_cols,
has_counts_difference, combine_counts,
h_tab_rsp_one_biomarker, arrange_grobs,
a_count_patients_sum_exposure, a_coxreg,
groups_list_to_df, forest_viewport.README to include installation instructions for
CRAN.indent_mod argument and replaced
it with the .indent_mods argument in
summarize_num_patients and
analyze_num_patients.s_coxreg and summarize_coxregto
work with new analysis function a_coxreg.section_div and na_level arguments
to summarize_vars.median_range as a numeric variable statistic
option for summarize_vars.d_onco_rsp_label.g_km
function.a_count_patients_sum_exposure for
summarize_patients_exposure_in_cols and new analyze
function analyze_patients_exposure_in_cols.s_proportion_diff.s_summary and s_compare to allow
NA values in input variables. For factor variables with
NAs, if na.rm = FALSE an explicit
NA level will be automatically added.
na.rm = TRUE will also consider
"<Missing>" values and exclude them.na_level parameter in
s_summary and s_compare to align with other
tern functions. Instead of being a string to consider as
NA when setting na.rm = TRUE, it now defines a
string to print in place of NA values in the output
table.TRTEDTM in tern
datasets.na_level argument in
summarize_vars preventing it from having an effect.lubridate package for date variables in
tern datasets..gitignore and .Rbuildignore
files.footnotes functions and all related
files.pairwise function.count_patients_with_flags functions from
count_patients_with_event.R to
count_patients_with_flags.R.summarize_glm_count function to analyze count
data using a linear model.g_step.format_fraction_fixed_dp and
format_count_fraction_fixed_dp with fixed single decimal
place in percentages.na_level and labelstr arguments to
summarize_vars_in_cols.analyze_num_patients to include summary at the
beginning that does not repeat when paginating.h_row_first_values function as a more general
helper function to retrieve first values from specific rows."(n)" suffix from
unique_count labels for s_num_patients.g_km to annotate with statistics
(annot_stats) and add corresponding vertical lines
(annot_stats_lines).s_count_occurrences_by_grade.summarize_vars_in_cols to work with
pagination machinery.conf_level argument to
emmeans::contrast() in s_ancova.rtables_access.R caused by not checking
for specific combinations (also the standard values that were never
used) of column indices and names.count_abnormal_by_grade.add_rowcounts that caused all row count
row values to count as zero.h_col_indices causing an error when
pruning with combination columns.test_proportion_diff missing argument for
var_labels.pkgdown reference..R files for logistic regression and
cox regression helper functions.analyze_num_patients to
generate an initial summary so there is no repetition when
paginating.testthat 3rd edition and replaced
applicable tests with snapshot testing.summarize_ancova examples to use
iris dataset instead of scda data.data/ folder and generated cached synthetic
datasets.data/ folder instead of scda datasets.tern. These tests are
in internal repo scda.test.summarize_vars_in_cols to
analyze_vars_in_cols to reflect the appropriate
analyze logic.summary_in_cols helper
functions.format_xx.ggplot2 functions/arguments to fix
warnings.forcats::fct_explicit_na
with forcats::fct_na_value_to_level.wrap_text function and related
files.footnotes functions.estimate_proportion and
estimate_proportion_diff with relative tests.stat_mean_pval, a new summary statistic to
calculate the p-value of the mean.mean_se (mean with standard error) for
summarize_variables and related functions.Rdpack for references.DescTools::BinomDiffCI function within
tern.summarize_logistic to specify
which pivoted value to use during analysis.s_coxph_pairwise to generate log-rank p-value
using original log-rank test instead of Cox Proportional-Hazards
Model.nestcolor in all examples by adapting
g_km, g_ipp, g_waterfall,
g_step, g_lineplot, and
g_forest.interaction_y and
interaction_item in ANCOVA to make the interaction
calculations available.footnotes to add footnotes to
g_km.assertthat to checkmatecheckmate::assert_vector,
checkmate::assert_set_equal, and
checkmate::assert_int to check vector type, length, and
values.checkmate the
following functions: all_elements_in_ref,
is_df_with_nlevels_factor,
is_df_with_no_na_level, is_proportion_vector,
is_quantiles_vector, is_character_or_factor,
is_nonnegative_count, is_valid_character,
assert_character_or_factor,
assert_equal_length and
has_tabletree_colnames.is_proportion, is_equal_length,
is_df_with_no_na_level,
is_df_with_nlevels_factor, is_variables,
is_df_with_variables, is_df_with_factors,
is_valid_factor to use assertion logic.as_factor_keep_attributes.assert_df_with_factors and
assert_proportion_value internal functions.assertthat.R and test-assertthat.R
to utils_checkmate.R and
test-utils_checkmate.R.count_abnormal_by_marked (reference to
abnormal_by_marked),
count_abnormal_lab_worsen_by_baseline and
h_adlb_worsen (reference to
abnormal_by_worst_grade_worsen_from_baseline),
count_abnormal_by_worst_grade (reference to
abnormal_by_worst_grade), to_string_matrix,
tidy.summary.coxph, tidy.step,
surv_timepoint, (reference to
survival_timepoint), surv_time (reference to
survival_time), coxph_pairwise (reference to
survival_coxph_pairwise),
extract_survival_subgroups and
tabulate_survival_subgroups (reference to
survival_duration_subgroups),
extract_survival_biomarkers and
tabulate_survival_biomarkers (reference to
survival_biomarkers_subgroups),
control_summarize_vars, s_summary and
a_summary (reference to summarize_variables)
and kept the S3 method tree.summarize_patients_exposure_in_cols,
summarize_num_patients with s_num_patients,
s_num_patients_content,
summarize_num_patients.count_cumulative, count_missed_doses,
count_patients_events_in_cols,
summarize_colvars, summarize_change,
summarize_ancova,as.rtable,
color_palette, add_footnotes.control_coxreg,
control_coxph, control_incidence_rate,
control_lineplot_vars, control_surv_time,
control_surv_timepoint, control_logisitic,
control_step.stat_mean_ci, stat_median_ci,
split_cols_by_groups, explicit_na,
sas_na, extract_rsp_subgroups,
tabulate_rsp_subgroups,
extract_rsp_biomarkers,
tabulate_rsp_biomarkers, keep_rows,
keep_content_rows, has_count_in_any_col,
has_fraction_in_cols, has_fraction_in_any_col,
has_fractions_difference,
test_proportion_diff, pairwise,
logistic_regression, estimate_incidence_rate,
control_incidence_rate (reference to
incidence_rate), cut_quantile_bins,
estimate_multinomial_rsp, decorate_grob_set,
extreme_format, fit_rsp_step,
fit_survival_step, footnotes,
footnotes-set, format_count_fraction,
format_fraction_threshold,
formatting_functions, format_fraction,
combination_function (S4 method),
compare_variables (S3 method),
kaplan_meier._pkgdown.yml
updated, and tern::: added for tests/examples/vignettes
where present for the following functions:
abnormal_by_marked)
s_count_abnormal_by_marked,
a_count_abnormal_by_marked.abnormal_by_worst_grade_worsen_from_baseline)
a_count_abnormal_lab_worsen_by_baseline,
s_count_abnormal_lab_worsen_by_baseline.abnormal_by_worst_grade)
s_count_abnormal_by_worst_grade,
a_count_abnormal_by_worst_grade.survival_timepoint)
s_surv_timepoint, s_surv_timepoint_diff,
a_surv_timepoint, a_surv_timepoint_diff.survival_time)
s_surv_time, a_surv_time.survival_coxph_pairwise)
s_coxph_pairwise, a_coxph_pairwise.survival_duration_subgroups)
a_survival_subgroups.count_cumulative)
s_count_cumulative, a_count_cumulative.count_missed_doses)
s_count_nonmissing, s_count_missed_doses,
a_count_missed_doses.count_patients_events_in_cols)
s_count_patients_and_multiple_events,
summarize_patients_events_in_cols.incidence_rate)
s_incidence_rate, a_incidence_rate.cox_regression_inter,
decorate_grob_factory, draw_grob,
estimate_coef.summary_labels, summary_formats,
s_count_patients_sum_exposure,
a_change_from_baseline s_change_from_baseline,
a_ancova, s_ancova,
arrange_grobs, as_factor_keep_attributes,
combine_levels, split_text_grob,
groups_list_to_df, s_cox_multivariate,
is_leaf_table, a_response_subgroups,
range_noinf, has_count_in_cols,
has_counts_difference, prop_chisq,
prop_cmh, prop_schouten,
prop_fisher, s_test_proportion_diff,
a_test_proportion_diff, fct_discard,
fct_explicit_na_if.stats::ancova output due to
version inconsistency.NA
coming from rtables.formatters::var_labels.prop_diff functions to respect success responses
(TRUE values).cut_quantile_bins.rtables split functions)s_ancova causing an error when the first
level of the arm factor is not the control arm.s_abnormal_by_worst_grade when there is
one PARAM level.prop_diff_wald when selecting all
responders, updated tests accordingly.h_ancova that caused an error when
deselecting all covariates.g_mmrm.tern:::)
and added dontrun to internal function examples.color_palette and
h_set_nest_theme in favor of
nestcolor::color_palette and
nestcolor::theme_nest, respectively.color_palette,
color_palette_core, h_set_nest_theme,
s_cox_univariate.fit_mmrm,
g_mmrm_diagnostic, g_mmrm_lsmeans,
as.rtable.mmrm, h_mmrm_fixed,
h_mmrm_cov, h_mmrm_diagnostic,
tidy.mmrm, s_mmrm_lsmeans,
s_mmrm_lsmeans_single, summarize_lsmeans.arm to study_arm and
extract to extract_by_name.rtables.R to utils_rtables.R.cox_regression_inter into a separate file
from cox_regression.estimate_incidence_rate.R to
incidence_rate.R to match the documentation grouping
name.control_incidence_rate into a separate file
because it produces a separate documentation file.@md and removed @order from
incidence_rate.R. Modified examples accordingly.prop_schouten function
documentation.draw_grob function.h_split_by_subgroups documentation warning fix for
wrong placing of example block@description
instead of every @descriptionIn function. Corrected
accordingly summarize_variables_in_colsg_lineplot, g_step,
g_waterfall, cox_regression,
score_occurrences, add_rowcounts,
odds_ratio, count_occurrences,
count_occurrences_by_grade, explicit_na,
df_explicit_na, count_patients_with_event,
decorate_grob, combine_groups,
append_varlabels, univariate,
stack_grobs, count_abnormal (reference to
abnormal), count_abnormal_by_baseline
(reference to abnormal_by_baseline)._pkgdown.yml
polished and tern::: for tests, examples, and vignettes
when present for the following functions:
h_format_row,
h_map_for_count_abnormalmake_names, month2day,
day2month empty_vector_if_na,
aesi_label, n_available,
format_xx, arm.count_values_funs, prop_difference,
combine_counts.s_count_abnormal,
a_count_abnormal.s_count_abnormal_by_baseline,
a_count_abnormal_by_baseline,
d_count_abnormal_by_baseline.s_cox_univariate function has now deprecated
badge.g_lineplot with table to automatically scale
the table height and return a ggplot object.g_ipp with caption argument and adjust the
position.prop_diff, tern function and
related functions to be able to apply a continuity correction in the
Newcombe method.summarize_numeric_in_columns and
summarize_variables to allow factor/character summary and
to be able to summarize the number of BLQs in
AVALC from ADPC dataset.sum option to
summarize_variables.stream by
default).h_pkparam_sort function with argument
key_var to allow data with different column names.test-table_aet02.R variant 12.scda data version to ‘2022-02-28’.pkgdown site.grDevices,
stringr, and viridisLite.summarize_numeric_in_columns to
summarize_variables_in_columns.summarize_vars_numeric_in_cols to
summarize_vars_in_cols.g_lineplot plot were
not connected when missing values.tern.mmrm.h_pkparam_sort to order PK PARAM
value based on the order of the dataset generated by
d_pkparam().d_pkparam to generate PK parameter map for
sorting.nudge_y argument of h_g_ipp to
be dependent on the data, fixing an issue whereby the baseline labels
were offset incorrectly.stat_mean_ci and
s_summary.numeric to calculate the geometric mean with its
confidence intervals.rtables package refactor.with_label, var_labels, and
var_labels<- to resolve conflict with the
formatters package, a new dependency.tern” and “tern
tabulation” vignettes.h_map_for_count_abnormal to create the map used
in trim_levels_to_map split function by calling this helper
function. It supports two methods: one with all observed mapping, one
with at least low limit above zero and at least one non missing high
limit.s_summary_numeric_in_cols and
summarize_vars_numeric_in_cols functions to generate
summary statistics in columns, mainly used for PK datasets.s_summary.numeric to use in
s_summary_numeric_in_cols.tabulate_survival_subgroups and
tabulate_rsp_subgroups (Survival Duration and Best Response
analyses) to calculate N-s based on the records considered
to create the model.estimate_proportion and related
functions to be able to apply a continuity correction in the Wilson
method.count_abnormal_by_marked and related
statistics and formatting functions to use a more efficient layout with
.spl_context argument used for determining denominators and
with trim_levels_to_map split function under
split_rows_by to show the desired levels in the table. This
is a breaking change.count_abnormal_by_worst_grade and related
statistics and formatting functions to use a more efficient layout with
.spl_context argument used for determining denominators and
with trim_levels_to_map split function under
split_rows_by to show the desired levels in the table. This
is a breaking change.count_abnormal function and related
statistics and formatting functions to use a more efficient layout with
trim_levels_to_map split function under
split_rows_by to show the desired levels in the table. Also
updated abnormal argument to be able to consider more than
one level for each direction. This is a breaking change.estimate_incidence_rate and
related functions to consider the week as time unit for data input.assertthat functions that output wrong
data frame names and limited length of failure message outputs.utils.nest by using the
checkmate and purrr packages for validation
and moved get_free_cores and skip_if_too_deep
functions from utils.nest into tern.survival_biomarkers_subgroups and
response_biomarkers_subgroups.g_lineplot plot function, including new
h_format_row helper function and
control_lineplot_vars function. Removed
g_summary_by.h_stack_by_baskets to
stack events in SMQ and/or CQ basket flag in ADAE data set.s_summary.numeric.
Added names attribute to each element of the final list
returned by the s_summary.numeric function. Added
summary_formats and summary_labels helper
functions.df_explicit_na.h_append_grade_groups to improve its
flexibility, robustness and clearness, and to make sure the result is
ordering according to the order of grade_groups. Also,
added remove_single argument which controls whether the
elements of one-element grade groups are in the output or removed.var_labels and show_labels arguments
to count_occurrences and
count_patients_with_flags to allow for creation of a title
row.na_level argument to
count_abnormal_by_baseline.h_append_grade_groups to no longer fill-in
empty grade groups with zeros.prop_diff_cmh to handle edge case of no FALSE (or
TRUE) responses.g_mmrm_diagnostic to improve error handling
when data is not amenable to the Locally Weighted Scatterplot
Smoothing.g_km:
arm variable includes a single level and
annot_coxph = TRUE.day2month and month2day to work with
NA data.stat_mean_ci and
stat_median_ci so that they may return different
outputs.h_row_counts to handle analysis
rows with NULL cells.LICENCE and README with new
package references.error_on_lint: TRUE to .lintr.count_abnormal_by_marked tabulates marked laboratory
abnormalities.summarize_patients_exposure_in_cols tabulates patient
counts and sum of exposure across all patients.arm variable.cox_regression to work without covariates. Also
in case of interaction model summary, p-values for main effect
coefficients are no longer displayed.summarize_vars now
include quantiles. summarize_vars now accepts the control
function control_summarize_vars to specify details about
confidence level for mean and median and quantile details. The
control argument replaces conf_level.var_labels and show_labels arguments
to count_occurrences_by_grade.indent argument in
append_varlabels to accept non-negative integer to
represent the indent space defined by user. Previous calls with Boolean
indent will do an integer conversion and produce a
warning.tabulate_survival_subgroups and related
survival forest plot functions to use total number of events, instead of
observations, as default for scaling the symbol sizes in the plot. (The
user might still use total number of observations manually if they wish
to do so.)h_adsl_adlb_merge_using_worst_flag will
now impute BTOXGR for missing visits.count_abnormal_by_worst_grade_by_baseline and
its related statistic and analysis functions as a simpler design will
create lab abnormality tables.scda instead of
random.cdisc.data package.fit_rsp_step and fit_survival_step,
the corresponding tidy method tidy.step as well as the
graph function g_step.compare_vars which compares
variables of different types between columns and produces a p-value for
the comparison to the reference column. Function built on top of the
summarize_vars functionality.cut_quantile_bins cuts a numeric vector into quantile
bins.fct_collapse_only collapses levels of a factor and
keeps those in the order provided.fct_explicit_na_if inserts explicit missings in a
factor based on a condition.range_noinf is a kind of a wrapper function of
base::range. It returns c(NA, NA) instead of
c(-Inf, Inf) for zero-length data.fit_coxreg_univar and
fit_coxreg_multivar is now also possible without treatment
arm. In the univariate case this means that it fits separate univariate
models for the provided covariates and tabulation of corresponding
effect estimates can later occur.fraction in result returned by
s_count_occurrences. It contains a list of numerators and
denominators with one element per occurrence.sum_num_patients and
count_occurrences for the result unique and
count_fraction to return (0, 0) when input is empty.groups_lists to
extract_survival_subgroups,
extract_rsp_subgroups and associated helper functions which
allows to group factor levels of subgroup variables into manually
defined groups, enhancing the flexibility of the resulting forest
graphs.g_forest now extracts default
arguments from attributes of the input table produced by
tabulate_rsp_subgroups and
tabulate_survival_subgroups so that the user does not have
to do this manually anymore.g_km:
s_surv_time function to use a newly created
function range_noinf instead of
base::range.no_fillin_visits added to
h_adsl_adlb_merge_using_worst_flag to specify excluded
visits from the post-baseline worst toxicity grade output. Improved
h_adsl_adlb_merge_using_worst_flag to include variables
shared between adsl and adlb, along with
PARAM, PARAMCD, ATOXGR,
BTOXGR and optionally AVISIT,
AVISITN when by_visit = TRUE. Prior output
contained USUBJID, ARMCD,
PARAMCD, ATOXGR, and BTOXGR.s_surv_timepoint for cases when there are
zero patients at risk.stat_median_ci function so that when passing
empty var with empty name, no
row names contain missing values error would show.s_cox_univariate function, use
fit_coxreg_univar function instead.hr and hr_ci in
a_coxph_pairwise and median in s_surv_time to
align with STREAM.test-table_ttet01.R and test-table_dort01.R to
make sure the analysis variable EVNT1 has both levels of
the factor defined.position_surv_med added to
g_km to move position of the annotation table with median
survival times.g_km related to the ignored arguments
pch and size which were not passed on to
helper function h_ggkm.xticks and max_time arguments in
g_km for greater functionality. max_time added
as an argument in h_xticks to allow this.prop_diff_cmh that led to NaN
weighted proportion difference estimates and missing confidence
intervals. Before this change, when including no patients from one
treatment arm for at least one stratum the estimation did not lead to
numeric results.prop_cmh giving an error in case of at
least one stratum containing less than two observations.n_events added to
estimate_incidence_rate.denom added to
count_occurrences.yval and ci_ribbon added to
g_km.g_ipp along
with helpers h_g_ipp and
h_set_nest_theme.count_patients_with_events, now shows zero
counts without percentage.get_mmrm_lsmeans which did not allow MMRM
analysis of more than 3000 observations.stat_mean_ci and stat_median_ci to
handle edge cases with number of elements in input series equal to 1.
For such cases, NA_real_ is now returned, instead of
NA or +/-Inf for confidence interval (CI)
estimates.n_lim argument of stat_mean_ci to
n_min to better reflect its desired meaning.This version of tern introduces a major rewriting of
tern due to the change to layout based tabulation in
rtables. tern now does not build tables
directly anymore, instead it provides analysis functions to build
tables, see the examples. * Counting patients with abnormal values
post-baseline with count_abnormal. * Counting patients with
graded abnormal values with count_abnormal_by_worst_grade.
* Counting patients with abnormal values by baseline status with
count_abnormal_by_baseline. * Counting patients with missed
doses with s_count_missed_doses and
count_missed_doses. * Counting patients with event flags
with count_patients_with_event and
count_patients_with_flags. * Summarizing variables with
summarize_vars (supports numeric, factor, character and
logical variables). Note that factors need to have NAs
converted to na_level before use. * Summarizing change from
baseline with summarize_change. * Summarizing variables in
columns with summarize_colvars. * Estimating difference for
responder proportions with estimate_proportion_diff. *
Estimating difference for Odds Ratio with
estimate_odds_ratio. * Testing the difference in responder
proportions with test_proportion_diff. * Estimating the
responder proportion for the level of a factor with
estimate_multinomial_response. * Fitting and tabulating the
results of Cox regressions with fit_coxreg_univar,
fit_coxreg_multivar and summarize_coxreg,
respectively. * Pruning occurrence tables (or tables with counts and
fractions) with flexible rules, see ?prune_occurrences for
details. * Sorting occurrence tables using different options, see
?score_occurrences for details. * Fitting and tabulating
MMRM models with fit_mmrm and as.rtable and
summarize_lsmeans, see ?tabulate_mmrm for
details. * Counting the number of unique and non-unique patients with
summarize_num_patients. * Counting occurrences with
count_occurrences. * Counting occurrences by grade with
summarize_occurrences_by_grade and
count_occurrences_by_grade. * Counting patients and events
in columns with summarize_patients_events_in_cols. *
Tabulating the binary outcome response by subgroup with
extract_rsp_subgroups and
tabulate_rsp_subgroups. * Tabulating the survival duration
by subgroup with extract_survival_subgroups and
tabulate_survival_subgroups.
a_mean_sd, a_median,
a_n_true_and_freq, a_count,
a_q1q3, a_iqr, a_range.s_test_proportion_diff:
Chi-Squared Test with Schouten Correction.t_contingency for contingency
tables.splitText to
dynamicSplitText to resolve the name conflict with the
package ggpubr.rreplace_format for tabulation
post-processing.t_ancova to create ANCOVA tables,
as well as corresponding elementary table function
t_el_ancova and summary function
s_ancova.s_odds_ratio to estimate Odds
Ratio of response between categories, as well as the corresponding
elementary table function t_el_odds_ratio.agresti-coull,
jeffreys) for s_proportion.anderson-hauck and
newcombe to s_proportion_diff.s_test_proportion_diff.t_binary_outcome
takes now lists (instead of character vectors) specified by the helper
function control_binary_comparison as the arguments
strat_analysis and unstrat_analysis. Odds
Ratio estimates and CIs are now removable and included by default,
similarly to the other subsections of the arm comparison analyses. Also
added argument rsp_multinomial.t_el_multinomial_proportion.t_abn_shift.s_mmrm, as well as
corresponding table functions t_mmrm_lsmeans,
t_mmrm_cov, t_mmrm_diagnostic,
t_mmrm_fixed, and plot functions
g_mmrm_lsmeans, g_mmrm_diagnostic. The results
of these match SAS results (up to numeric precision).a_mmrm and
t_mmrm (they give a deprecation warning but still work) to
remove in the next release. The reason is that the results of these
functions don’t match SAS results.g_km related to numbers in patients at risk
table to correct numbers for integer time-to-event variable inputs.row_by argument, inputs no longer
require use of nested_by.stat_mean_ci and stat_median_ci for
error bars in ggplot2.t_coxreg as single interface for
diverse cox regression types.t_binary_endpoint and elementary functions:
t_el_proportion, t_el_proportion_diff and
t_el_test_proportion_diff. The supporting summary functions
added are: s_proportion,
s_adj_proportion_diff, s_proportion_diff and
s_test_proportion_diff.t_events_patyear to create
event table adjusted person-years.t_abnormality and the
elementary table function t_el_abnormality.grade_levels argument from
t_events_term_grade_id functions. Post-processing by
reordering the leaves of the table tree creates a different ordering of
rows if required. Creating a helper function will occur at a later
time.prune_zero_rows argument to
t_events_per_term_grade_id and
t_max_grade_per_id to not show rows of all zeros as they
can clutter the visualization in the Shiny app and make it slower.t_summary_by output when
summarizing numeric columns in parallel with
compare_in_header.t_coxph to t_coxph_pairwise to
reflect the model process, add details in documentation.test.nest dependency.test.nest dependency.N in
t_summary.t_logistic for multi-variable logistic
regression table.df_explicit_na to replace
NA by explicit values.t_tte to specify confidence level
independent for survfit, coxph, and
ztest, see the manual.t_rsp of not showing p-value, odds ratio
and CIs when strata_data is not NULL.t_forest_rsp and
t_forest_tte, with footnotes in g_forest.footnotes, footnotes<- and
add_footnotes<- functions to deal with footnotes.conf_int for confidence interval level
to t_el_forest_rps, t_forest_rsp,
t_el_forest_tte, t_forest_tte.col_symbol_size to g_forest
to control the relative size of symbols used in the plot.s_coxph_pairwise function to perform pairwise
testing, used by t_tte and t_coxph.t_count_true replacing
t_summary_true.t_count_unique to create analysis subsets,
added t_el_count_unique for vectors.t_events_term_id so that table sort order
is by decreasing frequency instead of alphabetical.color_palette and a new nest color
palette.utils.nest.event_type argument to
t_events_per_term_grade_id.t_summary_by.node S4 class to create trees:
rtables.keys and keys<- functions.tabulate_pairwise.get_N, col_N_add_total,
check_id.na_as_level.as_factor_keep_attributes.r_by.t_el_disposition.t_el_forest_tte, t_el_forest_rsp.table_tree argument which returns a
node object.t_summary.numeric:
f_numeric to choose which statistics to
calculate.t_summary.factor:
denominator now also allows for omit if
wanting to omit percentages.t_summary_by:
by to row_by.t_forest_rsp, t_forest_tte:
group_data using
row_by_list.na_omit_group.t_count_unique:
indent argument, use the indent
function in rtables. insteadrandom.cdisc.data to speed up
testing.t_summary.Date method.save_join.test.nest tests:
width_row.names argument of
g_forest function into width_row_names.censor.show argument of g_km
function into censor_show.col.legend.title argument of
g_waterfall function into
col_legend_title.na.rm argument of t_count_unique
function into na_rm.row.name argument of
t_count_unique function into row_name.na.omit.group argument of
t_forest_rsp function into na_omit_group.na.omit.group argument of
t_forest_tte function into na_omit_group.row.name.TRUE and row.name.FALSE
arguments of t_summary.logical into
row_name_true and row_name_false
respectively.splotTextGrob into
split_text_grob.addTable,
t_summarize_by_visit,
t_summarize_variables.t_summary_by function.g_km function, renamed kmGrob
into kmCurveGrob.t_events_* family of functions.t_summary and methods for data.frame,
numeric, logical, character,
factor, and Date objects.t_events_per_term_id,
t_events_per_term_grade_id: Adverse Events &
Concomitant Treatment Tables.t_max_grade_per_id, t_count_unique,
t_events_summary elementary tables used for the Adverse
Events & Concomitant Treatment Tables.g_waterfall: Horizontal Waterfall Plot.decorate_grob, decorate_grob_set,
decorate_grob_factory, splitTextGrob.stack_grobs, arrange_grobs,
draw_grob.t_tte now shows two rows with ranges for event and
censored times, respectively.g_km works with one arm survfit
objects.t_summarise_variables uses now n instead
of N as a denominator for calculating percentages for
factors by default.t_rsp now works when all response values are
TRUE or FALSE.t_summarize_variables as
t_summary is more powerful.t_summarize_by_visit with
t_summary_by will occur in an upcoming release.