Helper function for ggstatsplot::ggbarstats to apply this function across multiple levels of a given factor and combining the resulting plots using ggstatsplot::combine_plots.

grouped_ggbarstats(
  data,
  x = NULL,
  y = NULL,
  counts = NULL,
  grouping.var,
  title.prefix = NULL,
  output = "plot",
  main,
  condition,
  ...,
  plotgrid.args = list(),
  title.text = NULL,
  title.args = list(size = 16, fontface = "bold"),
  caption.text = NULL,
  caption.args = list(size = 10),
  sub.text = NULL,
  sub.args = list(size = 12)
)

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 variable to use as the rows in the contingency table.

y

The variable to use as the columns in the contingency table. Default is NULL. If NULL, one-sample proportion test (a goodness of fit test) will be run for the x variable. Otherwise an appropriate association test will be run. This argument can not be NULL for ggbarstats function.

counts

A string naming a variable in data containing counts, or NULL if each row represents a single observation (Default).

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). If NULL, the variable name entered for grouping.var will be used.

output

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 set results.subtitle = FALSE, then this will return a NULL. Setting this to "caption" will return the expression containing details about Bayes Factor analysis, but valid only when type = "parametric" and bf.message = TRUE, otherwise this will return a NULL. For functions ggpiestats and ggbarstats, setting output = "proptest" will return a dataframe containing results from proportion tests.

main

The variable to use as the rows in the contingency table.

condition

The variable to use as the columns in the contingency table. Default is NULL. If NULL, one-sample proportion test (a goodness of fit test) will be run for the x variable. Otherwise an appropriate association test will be run. This argument can not be NULL for ggbarstats function.

...

Arguments passed on to ggbarstats

xlab

Custom text for the x axis label (Default: NULL, which will cause the x axis label to be the x variable).

ylab

Custom text for the y axis label (Default: NULL).

proportion.test

Decides whether proportion test for main variable is to be carried out for each level of y (Default: TRUE).

label

Character decides what information needs to be displayed on the label in each pie slice. Possible options are "percentage" (default), "counts", "both".

sample.size.label

Logical that decides whether sample size information should be displayed for each level of the grouping variable y (Default: TRUE).

ratio

A vector of proportions: the expected proportions for the proportion test (should sum to 1). Default is NULL, which means the null is equal theoretical proportions across the levels of the nominal variable. This means if there are two levels this will be ratio = c(0.5,0.5) or if there are four levels this will be ratio = c(0.25,0.25,0.25,0.25), etc.

paired

Logical indicating whether data came from a within-subjects or repeated measures design study (Default: FALSE). If TRUE, McNemar's test subtitle will be returned. If FALSE, Pearson's chi-square test will be returned.

results.subtitle

Decides whether the results of statistical tests are to be displayed as a subtitle (Default: TRUE). If set to FALSE, only the plot will be returned.

label.args

Additional aesthetic arguments that will be passed to geom_label.

conf.level

Scalar between 0 and 1. If unspecified, the defaults return 95% lower and upper confidence intervals (0.95).

k

Number of digits after decimal point (should be an integer) (Default: k = 2L).

perc.k

Numeric that decides number of decimal places for percentage labels (Default: 0).

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).

sampling.plan

Character describing the sampling plan. Possible options are "indepMulti" (independent multinomial; default), "poisson", "jointMulti" (joint multinomial), "hypergeom" (hypergeometric). For more, see ?BayesFactor::contingencyTableBF().

fixed.margin

For the independent multinomial sampling plan, which margin is fixed ("rows" or "cols"). Defaults to "rows".

prior.concentration

Specifies the prior concentration parameter, set to 1 by default. It indexes the expected deviation from the null hypothesis under the alternative, and corresponds to Gunel and Dickey's (1974) "a" parameter.

subtitle

The text for the plot subtitle. Will work only if results.subtitle = FALSE.

caption

The text for the plot caption.

legend.title

Title text for the legend.

ggtheme

A function, ggplot2 theme name. Default value is ggplot2::theme_bw(). Any of the ggplot2 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 selected ggtheme (Default: TRUE). theme_ggstatsplot is an opinionated theme layer that override some aspects of the selected ggtheme.

package

Name of the package from which the given palette is to be extracted. The available palettes and packages can be checked by running View(paletteer::palettes_d_names).

palette

Name of the package from which the given palette is to be extracted. The available palettes and packages can be checked by running View(paletteer::palettes_d_names).

ggplot.component

A ggplot component to be added to the plot prepared by ggstatsplot. This argument is primarily helpful for grouped_ variant of the current function. Default is NULL. The argument should be entered as a function.

plotgrid.args

A list of additional arguments to cowplot::plot_grid.

title.text

String or plotmath expression to be drawn as title for the combined plot.

title.args

A list of additional arguments provided to title, caption and sub, resp.

caption.text

String or plotmath expression to be drawn as the caption for the combined plot.

caption.args

A list of additional arguments provided to title, caption and sub, resp.

sub.text

The label with which the combined plot should be annotated. Can be a plotmath expression.

sub.args

A list of additional arguments provided to title, caption and sub, resp.

Value

Unlike a number of statistical softwares, ggstatsplot doesn't provide the option for Yates' correction for the Pearson's chi-squared statistic. This is due to compelling amount of Monte-Carlo simulation research which suggests that the Yates' correction is overly conservative, even in small sample sizes. As such it is recommended that it should not ever be applied in practice (Camilli & Hopkins, 1978, 1979; Feinberg, 1980; Larntz, 1978; Thompson, 1988).

For more about how the effect size measures and their confidence intervals are computed, see ?rcompanion::cohenG, ?rcompanion::cramerV, and ?rcompanion::cramerVFit.

See also

Examples

# \donttest{ # for reproducibility set.seed(123) # let's create a smaller dataframe diamonds_short <- ggplot2::diamonds %>% dplyr::filter(.data = ., cut %in% c("Very Good", "Ideal")) %>% dplyr::filter(.data = ., clarity %in% c("SI1", "SI2", "VS1", "VS2")) %>% dplyr::sample_frac(tbl = ., size = 0.05) # plot ggstatsplot::grouped_ggbarstats( data = diamonds_short, x = color, y = clarity, grouping.var = cut, title.prefix = "Quality", bar.label = "both", plotgrid.args = list(nrow = 2) )
#> Warning: Chi-squared approximation may be incorrect
# }