CRAN release: 2022-05-20
pairwise_comparisons()function to carry out pairwise comparison tests for one-way designs.
Expressions with statistical details were sometimes in a column named
label, while other times in
expressioncolumn. Now it will be consistently in the
Additionally, glue expressions were stored parsed in some data frame outputs, while unparsed in others. Now it is consistently parsed.
top.textparameter has been removed from all functions. It was relevant only in the context of ggstatsplot package. As that package no longer uses it, it is no longer necessary to retain it.
CRAN release: 2022-03-29
- Fixes breakages due to insight package update.
CRAN release: 2022-01-14
format_num()has been removed in favor of
expr_template()has been renamed to more informative
add_expression_col()function and has a different API. It returns a dataframe with the additional expression column instead of just the expression.
CRAN release: 2021-10-19
A number of effect size estimates and their confidence intervals have changed due to respective changes made in effectsize package version
0.5release. For full details of these changes, see: https://easystats.github.io/effectsize/news/index.html
For the same reason, the effect size for one-way contingency table has changed from Cramer’s V to Pearson’s C.
centrality_description()function added to describe distribution for each level of a grouping variable and create an expression describing a centrality measure.
Adds new experimental function
tidy_model_expressions()to create expressions for dataframes containing tidied results from regression model objects.
Removes the redundant
tidy_model_parametersdoes the same thing.
Exports more utility functions (
stats_type_switch) to get rid of reliance on
To be consistent with the expressions, the dataframe for Bayesian analysis now also contain log of Bayes Factor values.
tidy_model_effectsize()function is no longer exported as it is helpful only for the internal workings of the package.
Given that these values can be really high, the statistic values for non-parametric tests were shown on a log scale, but this is a highly non-standard practice that has caused a lot of confusion among users. In light of this feedback, the functions no longer return these values on a log scale but in a scientific notation to keep the statistical expressions short.
VR_dilemmadataset, which lacked enough variation to be a good dataset to use in examples or tests.
CRAN release: 2021-05-30
The effect size for independent trimmed means two-sample test has been changed from explanatory measure of effect size to AKP’s delta, which is easier to understand and interpret since its a robust cousin of Cohen’s d.
alternativeargument to specify alternative hypothesis (#86).
Cohen’s d and Hedge’s g use non-pooled standard deviation (cf. https://psyarxiv.com/tu6mp/).
- The output dataframes now contain columns with additional information about how confidence intervals are computed (thanks to
CRAN release: 2021-04-13
- Retires all vestigial
- Adapts failing tests due to changes in
CRAN release: 2021-03-11
This is the first stable release of statsExpressions!
There is good news and there is bad news that accompanies this milestone.
The bad news: The
APIfor the package has changed completely: All functions return a dataframe, and not an expression, as a default. The expression is contained in a list column in the dataframe itself. So, to salvage your functions from breaking, you will have to add
$expression[]to your function calls. For example, if you were using the function
expr_t_onesample(), you will now have to specify
expr_t_onesample()$expression[], so on and so forth. But, in general, the advice is to not use any of the
expr_*functions, which are vestigial names for new avatars of these function and will be removed in future. The new names are more intuitive, e.g.,
expr_t_onesample()is now called
The good news: There will not be any new changes to any of the current functions, except for any change necessary for maintenance or bug squashing. Well, to be more precise, this is true only for the functions that have “stable” badge.
- If the entered dataframe is
grouped-tibble, the function internally ungroups this (#79).
- To reduce dependency load,
afexhas moved from
CRAN release: 2021-02-19
- To avoid confusion among users, the trimming level for all functions is now changed from
tr = 0.1to
tr = 0.2(which is what
expr_templategains a new argument
bayesian, which can return an expression for Bayesian analysis, which has a slightly different template. Additionally, it has changed its conventions about the column names it expects.
Retires the additional caption-making functionality that was unique to
type = "parametric". This was the only context in which this feature was supported and was therefore inconsistent with the rest of the package API.
tidy_model_performancefunction, which is no longer used internally.
Removes column containing
logvalues of Bayes Factor as they are relevant only for expressions.
All meta-analysis packages move from
Suggeststo reduce the installation time for the user.
All robust tests in this package were based on trimmed means, except for correlation test. This has been changed: the robust correlation measure is now Winsorized correlation, which is based on trimming. Therefore, the
betaargument has been replaced by
trargument. This should result only in minor changes in correlation coefficient estimates.
CRAN release: 2021-01-19
To be consistent with
ggstatsplot’s overall syntax philosophy the
typeargument can be used to specify which type of statistical approach is to be used for all functions.
t_bayesare now removed in favor of a single function
expr_anova_bayesare now removed in favor of a single function
statsExpressions no longer internally relies on
tidyBF. All Bayesian analysis is carried out in this package itself. This was done to make the maintenance of this package easier and helps with some major internal code refactoring. As such, all re-exported functions from
tidyBFhave also been removed.
ratioargument while computing Cramer’s V for one-sample test. This is fixed.
All non-parametric functions now use
effectsizepackage to compute effect sizes and not
rcompanion. This would lead to some changes in effect sizes and their confidence intervals reported by the respective functions.
Robust one-sample test is changed from one-sample percentile bootstrap to bootstrap-t method for one-sample test, which uses trimmed mean like the rest of the robust functions in this package.
Package internally relies on
ezfor within-subjects ANOVA.
CRAN release: 2020-12-08
Internal refactoring to catch up with changes made to
effectsize. Tests are adapted to these changes as well.
Sample size information in expressions is pretty-formatted.
CRAN release: 2020-12-01
Adds two new helper functions:
tidy_model_performanceto toggle between
broomExtrafrom dependencies in favor of
Removes the unused and vestigial
CRAN release: 2020-10-30
Removes the alias
effsize.dfargument. Now all details need to be entered only in
All meta-analyses are now carried out using
expr_meta_randomand the individual functions have been removed.
All effect sizes for contingency tabs are now calculated via
rcompanion. This would lead to slight differences in effect sizes and their CIs but the computations will be faster. Additionally, the lower bound will never be negative and will be restricted to [0,1].
contingency_tablefunction has been made less robust. It now fails instead of returning
NULLwhen it is not supposed to work. This is done to be consistent with the other functions in the package which also fail instead of returning
expr_anova_parametricalways applies sphericity correction for p-values for repeated measures ANOVA.
expr_anova_parametricretires non-partial variants of effect sizes (eta-squared and omega-squared, i.e.) for parametric analyses.
The t-test and ANOVA tests get
subject.idargument relevant for repeated measures design.
Retires the vestigial
stat.titleargument. It was originally intended to give more info on the tests, but now the expressions themselves contain these details.
For paired ANOVA designs,
partial = TRUEis recognized by effect sizes.
bias.correctargument for contingency table analysis. It is rarely justifiable to use the biased version of Cramer’s V.
CRAN release: 2020-10-05
Adapts tests to changes made in the
Subtitles for correlation tests make clear the type of statistic.
Small p-values (< 0.001) are now shown in scientific format.
CRAN release: 2020-09-12
Adapts to changes made in
t_nonparametricsubtitle now clarifies whether it’s a Wilcoxon test or a Mann-Whitney test.
CRAN release: 2020-06-20
Thanks to Sarah, the package has a hexsticker. :)
Confidence intervals for Spearman’s rho are computed using
All relevant functions get rid of
messagesargument as the functions no longer print a message when bootstrapped CIs are used.
The effect size measure for paired robust t-test is now changed to robust (trimmed-Winsorized) standardized difference similar to Cohen’s d.
CRAN release: 2020-04-22
- Major bug introduced in
conf.leveldoesn’t work and function defaults to
- Removes extra space contained in subtitles for Bayes Factor results (#31).
CRAN release: 2020-04-15
Removes the experimental
All Bayes Factor related functions have now moved to the new
tidyBFpackage and are re-exported from there.
Minimum R version bumped to
Retires the internal
effsize_t_parametrichelper function in favor of relying functions from
effectsize, which is now added as a dependency. Similarly, statsExpressions now relies on
effectsizeto compute effect sizes for ANOVA designs, instead of
For parametric t-tests and ANOVAs, confidence intervals for effect sizes are estimated using the noncentrality parameter method. Centrality-based methods are deprecated.
Correlation analysis is carried out using
correlationpackage, which is now added as a dependency.
- All expressions now contain name of the statistical test carried out.
CRAN release: 2020-02-14
- Adds a new function
corr_objectsto reduce dependency load of
ggstatsplot. This is an experimental function and should be avoided until it stabilizes.
CRAN release: 2020-01-29
- New functions to carry out meta-analysis:
CRAN release: 2020-01-23
- New functions to carry out meta-analysis:
CRAN release: 2020-01-10
expr_templatefunction now expects two dataframes:
effsize.dfthat contain the details needed for creating expressions instead of providing each individual values. This makes the function more friendly work with using modeling packages like
Minor tweaks to how widehat is displayed in some of the expressions.
Cramer’s V is bias-corrected by default.
CRAN release: 2019-12-18
All effect size texts now contain
^on top to signify that these are estimates.
CRAN release: 2019-12-13
- Maintenance release to fix additional check issues on
CRAN release: 2019-08-28
Fixing tests for the new release of
Minor code refactoring.