grouped_ggbetweenstats
Violin plots for group or condition comparisons in between-subjects designs repeated across all levels of a grouping variable.
A combined plot of comparison plot created for levels of a grouping variable.
Usage
grouped_ggbetweenstats(
data,
x,
y,
grouping.var,
title.prefix = NULL,
plot.type = "boxviolin",
type = "parametric",
pairwise.comparisons = FALSE,
pairwise.annotation = "p.value",
pairwise.display = "significant",
p.adjust.method = "holm",
effsize.type = "unbiased",
partial = TRUE,
effsize.noncentral = TRUE,
bf.prior = 0.707,
bf.message = TRUE,
results.subtitle = TRUE,
xlab = NULL,
ylab = NULL,
subtitle = NULL,
stat.title = NULL,
caption = NULL,
sample.size.label = TRUE,
k = 2,
var.equal = FALSE,
conf.level = 0.95,
nboot = 100,
tr = 0.1,
sort = "none",
sort.fun = mean,
axes.range.restrict = FALSE,
mean.label.size = 3,
mean.label.fontface = "bold",
mean.label.color = "black",
notch = FALSE,
notchwidth = 0.5,
linetype = "solid",
outlier.tagging = FALSE,
outlier.label = NULL,
outlier.label.color = "black",
outlier.color = "black",
outlier.shape = 19,
outlier.coef = 1.5,
mean.plotting = TRUE,
mean.ci = FALSE,
mean.size = 5,
mean.color = "darkred",
point.jitter.width = NULL,
point.jitter.height = 0,
point.dodge.width = 0.6,
ggtheme = ggplot2::theme_bw(),
ggstatsplot.layer = TRUE,
package = "RColorBrewer",
palette = "Dark2",
direction = 1,
ggplot.component = NULL,
return = "plot",
messages = TRUE,
...
)
Arguments
- data
A dataframe (or a tibble) from which variables specified are to be taken. A matrix or tables will not be accepted.
- x
The grouping variable from the dataframe
data
.- y
The response (a.k.a. outcome or dependent) variable from the dataframe
data
.- grouping.var
A single grouping variable (can be entered either as a bare name
x
or as a string"x"
).- title.prefix
Character string specifying the prefix text for the fixed plot title (name of each factor level) (Default:
NULL
). IfNULL
, the variable name entered forgrouping.var
will be used.- plot.type
Character describing the type of plot. Currently supported plots are
"box"
(for pure boxplots),"violin"
(for pure violin plots), and"boxviolin"
(for a combination of box and violin plots; default).- type
Type of statistic expected (
"parametric"
or"nonparametric"
or"robust"
or"bayes"
).Corresponding abbreviations are also accepted:"p"
(for parametric),"np"
(nonparametric),"r"
(robust), or"bf"
resp.- pairwise.comparisons
Logical that decides whether pairwise comparisons are to be displayed (default:
FALSE
). Please note that only significant comparisons will be shown by default. To change this behavior, select appropriate option withpairwise.display
argument.- pairwise.annotation
Character that decides the annotations to use for pairwise comparisons. Either
"p.value"
(default) or"asterisk"
.- pairwise.display
Decides which pairwise comparisons to display. Available options are
"significant"
(abbreviation accepted:"s"
) or"non-significant"
(abbreviation accepted:"ns"
) or"everything"
/"all"
. The default is"significant"
. You can use this argument to make sure that your plot is not uber-cluttered when you have multiple groups being compared and scores of pairwise comparisons being displayed.- p.adjust.method
Adjustment method for p-values for multiple comparisons. Possible methods are:
"holm"
(default),"hochberg"
,"hommel"
,"bonferroni"
,"BH"
,"BY"
,"fdr"
,"none"
.- effsize.type
Type of effect size needed for parametric tests. The argument can be
"biased"
(equivalent to"d"
for Cohen's d for t-test;"partial_eta"
for partial eta-squared for anova) or"unbiased"
(equivalent to"g"
Hedge's g for t-test;"partial_omega"
for partial omega-squared for anova)).- partial
Logical that decides if partial eta-squared or omega-squared are returned (Default:
TRUE
). IfFALSE
, eta-squared or omega-squared will be returned. Valid only for objects of classlm
,aov
,anova
, oraovlist
.- effsize.noncentral
Logical indicating whether to use non-central t-distributions for computing the confidence interval for Cohen's d or Hedge's g (Default:
TRUE
).- bf.prior
A number between
0.5
and2
(default0.707
), the prior width to use in calculating Bayes factors.- bf.message
Logical that decides whether to display Bayes Factor in favor of the null hypothesis. This argument is relevant only for parametric test (Default:
TRUE
).- results.subtitle
Decides whether the results of statistical tests are to be displayed as a subtitle (Default:
TRUE
). If set toFALSE
, only the plot will be returned.- xlab
Labels for
x
andy
axis variables. IfNULL
(default), variable names forx
andy
will be used.- ylab
Labels for
x
andy
axis variables. IfNULL
(default), variable names forx
andy
will be used.- subtitle
The text for the plot subtitle. Will work only if
results.subtitle = FALSE
.- stat.title
A character describing the test being run, which will be added as a prefix in the subtitle. The default is
NULL
. An example of astat.title
argument will be something like"Student's t-test: "
.- caption
The text for the plot caption.
- sample.size.label
Logical that decides whether sample size information should be displayed for each level of the grouping variable
x
(Default:TRUE
).- k
Number of digits after decimal point (should be an integer) (Default:
k = 2
).- var.equal
a logical variable indicating whether to treat the variances in the samples as equal. If
TRUE
, then a simple F test for the equality of means in a one-way analysis of variance is performed. IfFALSE
, an approximate method of Welch (1951) is used, which generalizes the commonly known 2-sample Welch test to the case of arbitrarily many samples.- conf.level
Scalar between 0 and 1. If unspecified, the defaults return
95%
lower and upper confidence intervals (0.95
).- nboot
Number of bootstrap samples for computing confidence interval for the effect size (Default:
100
).- tr
Trim level for the mean when carrying out
robust
tests. If you get error stating "Standard error cannot be computed because of Winsorized variance of 0 (e.g., due to ties). Try to decrease the trimming level.", try to play around with the value oftr
, which is by default set to0.1
. Lowering the value might help.- sort
If
"ascending"
(default),x
-axis variable factor levels will be sorted based on increasing values ofy
-axis variable. If"descending"
, the opposite. If"none"
, no sorting will happen.- sort.fun
The function used to sort (default:
mean
).- axes.range.restrict
Logical that decides whether to restrict the axes values ranges to
min
andmax
values of the axes variables (Default:FALSE
), only relevant for functions where axes variables are of numeric type.- mean.label.size
Aesthetics for the label displaying mean. Defaults:
3
,"bold"
,"black"
, respectively.- mean.label.fontface
Aesthetics for the label displaying mean. Defaults:
3
,"bold"
,"black"
, respectively.- mean.label.color
Aesthetics for the label displaying mean. Defaults:
3
,"bold"
,"black"
, respectively.- notch
A logical. If
FALSE
(default), a standard box plot will be displayed. IfTRUE
, a notched box plot will be used. Notches are used to compare groups; if the notches of two boxes do not overlap, this suggests that the medians are significantly different. In a notched box plot, the notches extend1.58 * IQR / sqrt(n)
. This gives a roughly95%
confidence interval for comparing medians. IQR: Inter-Quartile Range.- notchwidth
For a notched box plot, width of the notch relative to the body (default
0.5
).- linetype
Character strings (
"blank"
,"solid"
,"dashed"
,"dotted"
,"dotdash"
,"longdash"
, and"twodash"
) specifying the type of line to draw box plots (Default:"solid"
). Alternatively, the numbers0
to6
can be used (0
for "blank",1
for "solid", etc.).- outlier.tagging
Decides whether outliers should be tagged (Default:
FALSE
).- outlier.label
Label to put on the outliers that have been tagged. This can't be the same as
x
argument.- outlier.label.color
Color for the label to to put on the outliers that have been tagged (Default:
"black"
).- outlier.color
Default aesthetics for outliers (Default:
"black"
).- outlier.shape
Hiding the outliers can be achieved by setting
outlier.shape = NA
. Importantly, this does not remove the outliers, it only hides them, so the range calculated for they
-axis will be the same with outliers shown and outliers hidden.- outlier.coef
Coefficient for outlier detection using Tukey's method. With Tukey's method, outliers are below (1st Quartile) or above (3rd Quartile)
outlier.coef
times the Inter-Quartile Range (IQR) (Default:1.5
).- mean.plotting
Logical that decides whether mean is to be highlighted and its value to be displayed (Default:
TRUE
).- mean.ci
Logical that decides whether
95%
confidence interval for mean is to be displayed (Default:FALSE
).- mean.size
Point size for the data point corresponding to mean (Default:
5
).- mean.color
Color for the data point corresponding to mean (Default:
"darkred"
).- point.jitter.width
Numeric specifying the degree of jitter in
x
direction. Defaults to40%
of the resolution of the data.- point.jitter.height
Numeric specifying the degree of jitter in
y
direction. Defaults to0.1
.- point.dodge.width
Numeric specifying the amount to dodge in the
x
direction. Defaults to0.60
.- ggtheme
A function,
ggplot2
theme name. Default value isggplot2::theme_bw()
. Any of theggplot2
themes, or themes from extension packages are allowed (e.g.,ggthemes::theme_fivethirtyeight()
,hrbrthemes::theme_ipsum_ps()
, etc.).- ggstatsplot.layer
Logical that decides whether
theme_ggstatsplot
theme elements are to be displayed along with the selectedggtheme
(Default:TRUE
).theme_ggstatsplot
is an opinionated theme layer that override some aspects of the selectedggtheme
.- package
Name of package from which the palette is desired as string or symbol.
- palette
Name of palette as string or symbol.
- direction
Either
1
or-1
. If-1
the palette will be reversed.- ggplot.component
A
ggplot
component to be added to the plot prepared byggstatsplot
. This argument is primarily helpful forgrouped_
variant of the current function. Default isNULL
. The argument should be entered as a function. If the given function has an argumentaxes.range.restrict
and if it has been set toTRUE
, the addedggplot
component might not work as expected.- return
Character that describes what is to be returned: can be
"plot"
(default) or"subtitle"
or"caption"
. Setting this to"subtitle"
will return the expression containing statistical results. If you have setresults.subtitle = FALSE
, then this will return aNULL
. Setting this to"caption"
will return the expression containing details about Bayes Factor analysis, but valid only whentype = "parametric"
andbf.message = TRUE
, otherwise this will return aNULL
.- messages
Decides whether messages references, notes, and warnings are to be displayed (Default:
TRUE
).- ...
Arguments passed on to
combine_plots
title.text
String or plotmath expression to be drawn as title for the combined plot.
title.color
Text color for title.
title.size
Point size of title text.
title.vjust
Vertical justification for title. Default =
0.5
(centered ony
).0
= baseline aty
,1
= ascender aty
.title.hjust
Horizontal justification for title. Default =
0.5
(centered onx
).0
= flush-left at x,1
= flush-right.title.fontface
The font face (
"plain"
,"bold"
(default),"italic"
,"bold.italic"
) for title.caption.text
String or plotmath expression to be drawn as the caption for the combined plot.
caption.color
Text color for caption.
caption.size
Point size of title text.
caption.vjust
Vertical justification for caption. Default =
0.5
(centered on y).0
= baseline at y,1
= ascender at y.caption.hjust
Horizontal justification for caption. Default =
0.5
(centered on x).0
= flush-left at x,1
= flush-right.caption.fontface
The font face (
"plain"
(default),"bold"
,"italic"
,"bold.italic"
) for caption.sub.text
The label with which the combined plot should be annotated. Can be a plotmath expression.
sub.color
Text color for annotation label (Default:
"black"
).sub.size
Point size of annotation text (Default:
12
).sub.x
The x position of annotation label (Default:
0.5
).sub.y
The y position of annotation label (Default:
0.5
).sub.hjust
Horizontal justification for annotation label (Default:
0.5
).sub.vjust
Vertical justification for annotation label (Default:
0.5
).sub.vpadding
Vertical padding. The total vertical space added to the label, given in grid units. By default, this is added equally above and below the label. However, by changing the y and vjust parameters, this can be changed (Default:
ggplot2::unit(1, "lines")
).sub.fontface
The font face (
"plain"
(default),"bold"
,"italic"
,"bold.italic"
) for the annotation label.sub.angle
Angle at which annotation label is to be drawn (Default:
0
).sub.lineheight
Line height of annotation label.
title.caption.rel.heights
Numerical vector of relative columns heights while combining (title, plot, caption).
title.rel.heights
Numerical vector of relative columns heights while combining (title, plot).
caption.rel.heights
Numerical vector of relative columns heights while combining (plot, caption).
Details
For parametric tests, Welch's ANOVA/t-test are used as a default (i.e.,
var.equal = FALSE
).
References:
ANOVA: Delacre, Leys, Mora, & Lakens, PsyArXiv, 2018
t-test: Delacre, Lakens, & Leys, International Review of Social Psychology, 2017
If robust tests are selected, following tests are used is .
ANOVA: one-way ANOVA on trimmed means (see
?WRS2::t1way
)t-test: Yuen's test for trimmed means (see
?WRS2::yuen
)
For more about how the effect size measures (for nonparametric tests) and
their confidence intervals are computed, see ?rcompanion::wilcoxonR
.
For repeated measures designs, use ggwithinstats
.
References
https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/ggbetweenstats.html
See Also
Examples
# NOT RUN {
# to get reproducible results from bootstrapping
set.seed(123)
# the most basic function call
ggstatsplot::grouped_ggbetweenstats(
data = dplyr::filter(ggplot2::mpg, drv != "4"),
x = year,
y = hwy,
grouping.var = drv,
conf.level = 0.99
)
# modifying individual plots using `ggplot.component` argument
ggstatsplot::grouped_ggbetweenstats(
data = dplyr::filter(
ggstatsplot::movies_long,
genre %in% c("Action", "Comedy"),
mpaa %in% c("R", "PG")
),
x = genre,
y = rating,
grouping.var = mpaa,
results.subtitle = FALSE,
ggplot.component = ggplot2::scale_y_continuous(
breaks = seq(1, 9, 1),
limits = (c(1, 9))
),
messages = FALSE
)
# }