ord_pairsto retrieve $N_c$, $N_d$, ties and total number of pairs for contingency tables. Internals for this function are straight up copied from this gist.
etasqin case you want to show students what $\eta^2$ is without having to explain ANOVA.
ord_somers_dnot returning the correct value for
symmetric = TRUE
sjlabelled::zap_labelsis a thing
ryoureadydependency, in favor of the more versatile
vcddependency, also in favor of
DescToolsfunctions are very similar to what the wrappers do, so the wrappers might be removed in the future.)
tadaa_intby being better at
dplyrdependency by being better at R.
havendependency by not re-exporting
sjmiscdepencency because why did we depend on that again?
sjlabelleddependency (only used for re-exports).
lsrdependency in favor of, you guessed it,
DescToolsfor eta in
tadaa_-test functions use
tadaatoolbox::pval_stringinstead of the
ngo, as it should be computed from
Suggestsbecause whe only need it in one function, sometimes.
ord_tauto calculate all the Taus
tadaa_pairwise_tas an extension of
stats::pairwise.t.testthat works with two grouping factors and thereby can test interactions.
tadaa_pairwise_ghfor the Games Howell post-hoc procedure as an alternative to
tadaa_pairwise_tukeywhile we’re at it. Just a thin wrapper for
stats::TukeyHSDbut with tidied output and usage consistent with the previous
tadaa_plot_tukeyto plot Tukey HSD results as error bars because boy do I like error bars.
tadaa_balanceas a replacement for
tadaa_heatmapto check equality of group sizes.
magrittras all the cool kids to these days.
magrittrbecause I happen to really like it.
sjmisc, as they’re handy.
havenas a replacement for the deprecated
theme_readthedown, will probably become the new canonical version.
xaxis title via proper margining.
3, for generally safer results and consistency with SPSS.
type = 3sums of squares, which ensures each non-ordered factor has
methods, which should fix an issue during
rmarkdownprocessing where the function
iscouldn’t be found. If not, manually
library(methods)as a workaround.
eta.sqto be formatted like a p-value.
show_powerargument to calculate power via
center = "median"for more robust results, as it should.
var.equalto override internal Levene test.
alternative = "less"or
conf.levelargument used for CI and power calculations
pairedargument so effects for paired tests are now a thing.
directionargument not being honored.
tadaa_one_sample: Should make sense now.
tadaa_wilcoxonbecause it’s problematic, and in case of
paired = TRUEit would have produced flat out wrong results.
print = markdownoutput of
print = "console"now has headers with unparsed $\LaTeX$-expressions, but who uses that anyway.
labels_to_factor: Was a wrapper around
haven::as_factorand is obsolete by now, as
as_factorcan do the same thing this function was built for.
tadaa_likertizeis renamed to
likertize, deprecated since
sjmisc::split_varis probably better anyway.
tadaa_aovnow knows about types, uses type 1 by default and can do types 2 and 3.
lsr::etaSquared, which also takes a
tadaa_mean_ci: Plots means with 95% confidence intervals as errorbars (thanks Christoph for the suggestion).
tadaa_one_sample: For one-sample t-tests and finally an easy z-test.
confint_norm: Helper to get CIs, similar to
tadaa_wilcoxon: For when
tadaa_t.testisn’t non-parametric enough. Same usage.
tadaa_kruskal: For when
tadaa_aovisn’t non-parametric enough, too.
mean_ci_sembecause it’s more
tadaa_int: Optionally display N in subtitle.
< 0.05. Well. That was embarrassing.
theme_readthedownregarding text placement.
tadaa_normtestlets you do tests for normality (4 methods) over multiple variables.
tadaa_heatmapgenerates a heatmap. Mhhh, heatmaps.
tadaa_semshows the standard error of the mean and it’s confidence interval
pval_stringas a modification of
p < .05.
tadaa_t.testand the new
tadaa_normtestnow return a
data.frameby default, allowing further shenanigans
grid = TRUEfor the two interaction plots to be printen in a grid via cowplot::plot_grid.
tadaa_intplot output now also is a little tidier and optimized for smaller widths.
tadaa_aovnow also shows Cohen’s f for easier power calculations based on f (
modus, so multiple results will be concatenated to a character by default.
modusbecause guessing about return value classes is no joke.
tadaa_ordas ordinal equivalent of
DESCRIPTIONare still experimental because of uncertainty regarding failing travis builds. I don’t know what’s going on there.
pixiedustdepends on R (>= 3.2.1), so we might as well depend on that version, too
broom, just to be safe
READMEto be less redundant compared to the usage vignette