ggstatsplot

https://indrajeetpatil.github.io/ggstatsplot
Admin
ggstatsplot is an R package that extends ggplot2 to create informative plots with integrated...
Tokens:81,113
Snippets:629
Trust Score:8.3
Update:6 months ago
Show doc for...
Tokens:
Raw
### Install ggstatsplot (Development)

Source: https://indrajeetpatil.github.io/ggstatsplot/index.html

Use this command to install the development version of the ggstatsplot package.

```R
pak::pak("IndrajeetPatil/ggstatsplot")
```

--------------------------------

### Preparing Data for ggdotplotstats

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/purrr_examples.html

Initial setup for ggdotplotstats by loading libraries and splitting the gapminder dataset.

```R
library(ggthemes)
library(hrbrthemes)

## let's split the data frame and create a list by continent
## let's leave out Oceania because it has just two data points
continent_list <-
  gapminder::gapminder %>%
  dplyr::filter(continent != "Oceania") %>%
  split(f = .$continent, drop = TRUE)
```

--------------------------------

### Inspecting Titanic_full dataset

Source: https://indrajeetpatil.github.io/ggstatsplot/reference/Titanic_full.html

Examples for checking dimensions, viewing the first few rows, and inspecting the structure of the dataset.

```R
dim(Titanic_full)
#> [1] 2201    5
head(Titanic_full)
#> # A tibble: 6 × 5
#>      id Class Sex   Age   Survived
#>   <dbl> <fct> <fct> <fct> <fct>   
#> 1     1 3rd   Male  Child No      
#> 2     2 3rd   Male  Child No      
#> 3     3 3rd   Male  Child No      
#> 4     4 3rd   Male  Child No      
#> 5     5 3rd   Male  Child No      
#> 6     6 3rd   Male  Child No      
dplyr::glimpse(Titanic_full)
#> Rows: 2,201
#> Columns: 5
#> $ id       <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18…
#> $ Class    <fct> 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3…
#> $ Sex      <fct> Male, Male, Male, Male, Male, Male, Male, Male, Male, Male, M…
#> $ Age      <fct> Child, Child, Child, Child, Child, Child, Child, Child, Child…
#> $ Survived <fct> No, No, No, No, No, No, No, No, No, No, No, No, No, No, No, N…
```

--------------------------------

### Install Ubuntu Dependencies for PMCMRplus

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/faq.html

Install `gmp` and `Rmpfr` libraries on Ubuntu to resolve installation issues with the PMCMRplus package, a dependency of ggstatsplot.

```bash
sudo apt-get install libgmp3-dev
```

```bash
sudo apt-get install libmpfr-dev
```

--------------------------------

### Inspecting the bugs_long dataset

Source: https://indrajeetpatil.github.io/ggstatsplot/reference/bugs_long.html

Demonstrates how to check the dimensions, view the first few rows, and get a summary of the data structure.

```R
dim(bugs_long)
#> [1] 372   6
head(bugs_long)
#> # A tibble: 6 × 6
#>   subject gender region        education condition desire
#>     <int> <fct>  <fct>         <fct>     <chr>      <dbl>
#> 1       1 Female North America some      LDLF           6
#> 2       2 Female North America advance   LDLF          10
#> 3       3 Female Europe        college   LDLF           5
#> 4       4 Female North America college   LDLF           6
#> 5       5 Female North America some      LDLF           3
#> 6       6 Female Europe        some      LDLF           2
dplyr::glimpse(bugs_long)
#> Rows: 372
#> Columns: 6
#> $ subject   <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 1…
#> $ gender    <fct> Female, Female, Female, Female, Female, Female, Female, Fema…
#> $ region    <fct> North America, North America, Europe, North America, North A…
#> $ education <fct> some, advance, college, college, some, some, some, high, hig…
#> $ condition <chr> "LDLF", "LDLF", "LDLF", "LDLF", "LDLF", "LDLF", "LDLF", "LDL…
#> $ desire    <dbl> 6.0, 10.0, 5.0, 6.0, 3.0, 2.0, 10.0, 10.0, 9.5, 8.5, 0.0, 9.…
```

--------------------------------

### Basic gghistostats for Reporting

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/gghistostats.html

A simple example of `gghistostats` to demonstrate how statistical results can be integrated into reports. This function visualizes data and provides statistical summaries.

```R
gghistostats(trees, Height, test.value = 75)
```

--------------------------------

### Install ggstatsplot (Release)

Source: https://indrajeetpatil.github.io/ggstatsplot/index.html

Use this command to install the stable release version of the ggstatsplot package from CRAN.

```R
install.packages("ggstatsplot")
```

--------------------------------

### Generate and analyze pie charts with ggpiestats

Source: https://indrajeetpatil.github.io/ggstatsplot/reference/ggpiestats.html

Demonstrates creating a one-sample goodness of fit proportion test plot and extracting statistical details using extract_stats, followed by an association test example.

```R
# for reproducibility
set.seed(123)

# one sample goodness of fit proportion test
p <- ggpiestats(mtcars, vs)

# looking at the plot
p


# extracting details from statistical tests
extract_stats(p)
#> $subtitle_data
#> # A tibble: 1 × 13
#>   statistic    df p.value method                                   effectsize 
#>       <dbl> <dbl>   <dbl> <chr>                                    <chr>      
#> 1       0.5     1   0.480 Chi-squared test for given probabilities Pearson's C
#>   estimate conf.level conf.low conf.high conf.method conf.distribution n.obs
#>      <dbl>      <dbl>    <dbl>     <dbl> <chr>       <chr>             <int>
#> 1    0.124       0.95        0     0.426 ncp         chisq                32
#>   expression
#>   <list>    
#> 1 <language>
#> 
#> $caption_data
#> # A tibble: 1 × 4
#>    bf10 prior.scale method                                      expression
#>   <dbl>       <dbl> <chr>                                       <list>    
#> 1 0.180           1 Bayesian one-way contingency table analysis <language>
#> 
#> $pairwise_comparisons_data
#> NULL
#> 
#> $descriptive_data
#> # A tibble: 2 × 4
#>   vs    counts  perc .label
#>   <fct>  <int> <dbl> <chr> 
#> 1 1         14  43.8 44%   
#> 2 0         18  56.2 56%   
#> 
#> $one_sample_data
#> NULL
#> 
#> $tidy_data
#> NULL
#> 
#> $glance_data
#> NULL
#> 
#> attr(,"class")
#> [1] "ggstatsplot_stats" "list"             

# association test (or contingency table analysis)
ggpiestats(mtcars, vs, cyl)
```

--------------------------------

### Create Pie Chart with Statistical Summary

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/purrr_examples.html

Utilize ggpiestats to generate pie charts with statistical analysis. This example splits data by passenger class and applies the function to each subset, customizing labels, palettes, and themes.

```R
class_list <- Titanic_full %>% split(f = .$Class, drop = TRUE)
```

```R
length(class_list)
names(class_list)
```

```R
plot_list <-
  purrr::pmap(
    .l = list(
      data = class_list,
      x = "Survived",
      y = "Sex",
      label = list("both", "count", "percentage", "both"),
      title = list(
        "Passenger class: 1st",
        "Passenger class: 2nd",
        "Passenger class: 3rd",
        "Passenger class: Crew"
      ),
      caption = list(
        "Total: 319, Died: 120, Survived: 199, % Survived: 62%",
        "Total: 272, Died: 155, Survived: 117, % Survived: 43%",
        "Total: 709, Died: 537, Survived: 172, % Survived: 25%",
        "Data not available for crew passengers"
      ),
      package = list("RColorBrewer", "ghibli", "palettetown", "yarrr"),
      palette = list("Accent", "MarnieMedium1", "pikachu", "nemo"),
      ggtheme = list(
        ggplot2::theme_grey(),
        ggplot2::theme_bw(),
        ggthemes::theme_tufte(),
        ggthemes::theme_economist()
      ),
      proportion.test = list(TRUE, FALSE, TRUE, FALSE),
      type = list("p", "p", "bf", "p")
    ),
    .f = ggpiestats
  )
```

```R
combine_plots(
  plotlist = plot_list,
  annotation.args = list(title = "Survival in Titanic disaster by gender for all passenger classes"),
  plotgrid.args = list(ncol = 1),
  guides = "keep"
)
```

--------------------------------

### Create a ggdotplotstats plot

Source: https://indrajeetpatil.github.io/ggstatsplot/reference/ggdotplotstats.html

Example of creating a dot plot with statistical details using ggdotplotstats. Requires ggplot2 and ggstatsplot packages.

```r
# for reproducibility
set.seed(123)

# creating a plot
p <- ggdotplotstats(
  data = ggplot2::mpg,
  x = cty,
  y = manufacturer,
  title = "Fuel economy data",
  xlab = "city miles per gallon"
)

# looking at the plot
p
```

--------------------------------

### Visualize Cox proportional hazards model with ggcoefstats

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/ggcoefstats.html

Visualize coefficients from a Cox proportional hazards regression model using ggcoefstats. Requires the survival package. This example demonstrates fitting a stratified model.

```R
library(survival)

# create the simplest-test data set
test1 <- list(
  time = c(4, 3, 1, 1, 2, 2, 3),
  status = c(1, 1, 1, 0, 1, 1, 0),
  x = c(0, 2, 1, 1, 1, 0, 0),
  sex = c(0, 0, 0, 0, 1, 1, 1)
)

# fit a stratified model
mod_coxph <-
  survival::coxph(
    formula = Surv(time, status) ~ x + strata(sex),
    data = test1
  )


ggcoefstats(
  x = mod_coxph,
  title = "Cox proportional hazards regression model"
)
```

--------------------------------

### Visualize Custom Data Frame with ggcoefstats

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/ggcoefstats.html

This example shows how to visualize a custom data frame using ggcoefstats. The data frame must include 'term' and 'estimate' columns, and optionally 'conf.low', 'conf.high', and 'p.value'. Specify the statistic type if needed.

```R
# let's create a data frame
df_full <- tibble::tribble(
  ~term, ~statistic, ~estimate, ~std.error, ~p.value, ~df.error,
  "study1", 0.158, 0.0665, 0.778, 0.875, 5L,
  "study2", 1.33, 0.542, 0.280, 0.191, 10L,
  "study3", 1.24, 0.045, 0.030, 0.001, 12L,
  "study4", 0.156, 0.500, 0.708, 0.885, 8L,
  "study5", 0.33, 0.032, 0.280, 0.101, 2L,
  "study6", 1.04, 0.085, 0.030, 0.001, 3L
)

ggcoefstats(
  x = df_full,
  meta.analytic.effect = TRUE,
  statistic = "t",
  package = "LaCroixColoR",
  palette = "paired"
)
```

--------------------------------

### Customized Correlation Matrix

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/ggcorrmat.html

Creates a detailed correlation matrix with custom variable names, correlation types, labels, themes, and color palettes. This example showcases extensive customization options for visual appeal and information display.

```R
ggcorrmat(
  data = gapminder_2007, ## data from which variable is to be taken
  cor.vars = lifeExp:gdpPercap, ## specifying correlation matrix variables
  cor.vars.names = c(
    "Life Expectancy",
    "population",
    "GDP (per capita)"
  ),
  type = "np", ## which correlation coefficient is to be computed
  lab.col = "red", ## label color
  ggtheme = ggplot2::theme_light(), ## selected ggplot2 theme
  ## turn off default ggestatsplot theme overlay
  matrix.type = "lower", ## correlation matrix structure
  colors = NULL, ## turning off manual specification of colors
  palette = "category10_d3", ## choosing a color palette
  package = "ggsci", ## package to which color palette belongs
  title = "Gapminder correlation matrix", ## custom title
  subtitle = "Source: Gapminder Foundation" ## custom subtitle
)
```

--------------------------------

### Extracting Statistical Analysis Summaries with ggstatsplot

Source: https://indrajeetpatil.github.io/ggstatsplot/index.html

This example shows the output of the `extract_stats` function, which returns a list of tibbles containing detailed statistical summaries for various analyses, such as ANOVA, pairwise comparisons, and Bayesian factors. These summaries are generated by the `statsExpressions` package.

```R
extract_stats(p)
#> $subtitle_data
#> # A tibble: 1 × 14
#>   statistic    df df.error    p.value
#>       <dbl> <dbl>    <dbl>      <dbl>
#> 1      31.6     2     18.0 0.00000127
#>   method                                                   effectsize estimate
#>   <chr>                                                    <chr>         <dbl>
#> 1 One-way analysis of means (not assuming equal variances) Omega2        0.744
#>   conf.level conf.low conf.high conf.method conf.distribution n.obs expression
#>        <dbl>    <dbl>     <dbl> <chr>       <chr>             <int> <list>    
#> 1       0.95    0.531         1 ncp         F                    32 <language>
#> 
#> $caption_data
#> # A tibble: 6 × 17
#>   term     pd prior.distribution prior.location prior.scale     bf10
#>   <chr> <dbl> <chr>                       <dbl>       <dbl>    <dbl>
#> 1 mu    1     cauchy                          0       0.707 3008850.
#> 2 cyl-4 1     cauchy                          0       0.707 3008850.
#> 3 cyl-6 0.780 cauchy                          0       0.707 3008850.
#> 4 cyl-8 1     cauchy                          0       0.707 3008850.
#> 5 sig2  1     cauchy                          0       0.707 3008850.
#> 6 g_cyl 1     cauchy                          0       0.707 3008850.
#>   method                          log_e_bf10 effectsize         estimate std.dev
#>   <chr>                                <dbl> <chr>                 <dbl>   <dbl>
#> 1 Bayes factors for linear models       14.9 Bayesian R-squared    0.714  0.0503
#> 2 Bayes factors for linear models       14.9 Bayesian R-squared    0.714  0.0503
#> 3 Bayes factors for linear models       14.9 Bayesian R-squared    0.714  0.0503
#> 4 Bayes factors for linear models       14.9 Bayesian R-squared    0.714  0.0503
#> 5 Bayes factors for linear models       14.9 Bayesian R-squared    0.714  0.0503
#> 6 Bayes factors for linear models       14.9 Bayesian R-squared    0.714  0.0503
#>   conf.level conf.low conf.high conf.method n.obs expression
#>        <dbl>    <dbl>     <dbl> <chr>       <int> <list>    
#> 1       0.95    0.574     0.788 HDI            32 <language>
#> 2       0.95    0.574     0.788 HDI            32 <language>
#> 3       0.95    0.574     0.788 HDI            32 <language>
#> 4       0.95    0.574     0.788 HDI            32 <language>
#> 5       0.95    0.574     0.788 HDI            32 <language>
#> 6       0.95    0.574     0.788 HDI            32 <language>
#> 
#> $pairwise_comparisons_data
#> # A tibble: 3 × 9
#>   group1 group2 statistic   p.value alternative distribution p.adjust.method
#>   <chr>  <chr>      <dbl>     <dbl> <chr>       <chr>        <chr>          
#> 1 4      6          -6.67 0.00110   two.sided   q            Holm           
#> 2 4      8         -10.7  0.0000140 two.sided   q            Holm           
#> 3 6      8          -7.48 0.000257  two.sided   q            Holm           
#>   test         expression
#>   <chr>        <list>    
#> 1 Games-Howell <language>
#> 2 Games-Howell <language>
#> 3 Games-Howell <language>
#> 
#> $descriptive_data
#> NULL
#> 
#> $one_sample_data
#> NULL
#> 
#> $tidy_data
#> NULL
#> 
#> $glance_data
#> NULL
#> 
#> attr(,"class")
#> [1] "ggstatsplot_stats" "list"
```

--------------------------------

### Get dimensions of iris_long

Source: https://indrajeetpatil.github.io/ggstatsplot/reference/iris_long.html

Returns the dimensions (number of rows and columns) of the iris_long dataset.

```R
dim(iris_long)
#> [1] 600   6
```

--------------------------------

### Load ggplot2 library

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/principles.html

Initializes the ggplot2 library for plotting.

```R
library(ggplot2)
```

--------------------------------

### Get Citation for ggstatsplot

Source: https://indrajeetpatil.github.io/ggstatsplot/index.html

Run this R code to obtain the citation information for the ggstatsplot package, useful for academic publications.

```R
citation("ggstatsplot")
```

--------------------------------

### Load Libraries and Inspect Data

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/gghistostats.html

Loads necessary libraries (psych, dplyr) and inspects the structure of the sat.act dataset using glimpse.

```R
library(psych)
library(dplyr)

## looking at the structure of the data using glimpse
dplyr::glimpse(psych::sat.act)
#> Rows: 700
#> Columns: 6
#> $ gender    <int> 2, 2, 2, 1, 1, 1, 2, 1, 2, 2, 1, 2, 1, 2, 2, 2, 2, 2, 1, 2, …
#> $ education <int> 3, 3, 3, 4, 2, 5, 5, 3, 4, 5, 3, 4, 4, 4, 3, 4, 3, 4, 4, 4, …
#> $ age       <int> 19, 23, 20, 27, 33, 26, 30, 19, 23, 40, 23, 34, 32, 41, 20, …
#> $ ACT       <int> 24, 35, 21, 26, 31, 28, 36, 22, 22, 35, 32, 29, 21, 35, 27, …
#> $ SATV      <int> 500, 600, 480, 550, 600, 640, 610, 520, 400, 730, 760, 710, …
#> $ SATQ      <int> 500, 500, 470, 520, 550, 640, 500, 560, 600, 800, 710, 600, …
```

--------------------------------

### Basic ggbarstats Plot

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/ggbarstats.html

A simple example of `ggbarstats` used with the `mtcars` dataset to visualize the relationship between transmission type and number of cylinders.

```r
ggbarstats(mtcars, am, cyl)
```

--------------------------------

### Visualize Bayesian Models

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/ggcoefstats.html

Shows how to visualize various Bayesian models from the BayesFactor package using ggcoefstats.

```R
library(BayesFactor)

# one sample t-test
mod1 <- ttestBF(mtcars$wt, mu = 3)

# independent t-test
mod2 <- ttestBF(formula = wt ~ am, data = mtcars)

# paired t-test
mod3 <- ttestBF(x = sleep$extra[1:10], y = sleep$extra[11:20], paired = TRUE)

# correlation
mod4 <- correlationBF(y = iris$Sepal.Length, x = iris$Sepal.Width)

# contingency tabs (not supported)
data("raceDolls")
mod5 <- contingencyTableBF(
  raceDolls,
  sampleType = "indepMulti",
  fixedMargin = "cols"
)

# anova
data("puzzles")
mod6 <- anovaBF(
  formula = RT ~ shape * color + ID,
  data = puzzles,
  whichRandom = "ID",
  whichModels = "top",
  progress = FALSE
)

# regression-1
mod7 <- regressionBF(rating ~ ., data = attitude, progress = FALSE)

# meta-analysis
t <- c(-0.15, 2.39, 2.42, 2.43, -0.15, 2.39, 2.42, 2.43)
N <- c(100, 150, 97, 99, 99, 97, 100, 150)
mod8 <- meta.ttestBF(t, N, rscale = 1, nullInterval = c(0, Inf))

# proportion test
mod9 <- proportionBF(y = 15, N = 25, p = 0.5)

# list of plots
combine_plots(
  plotlist = list(
    ggcoefstats(mod1, title = "one sample t-test"),
    ggcoefstats(mod2, title = "independent t-test"),
    ggcoefstats(mod3, title = "paired t-test"),
    ggcoefstats(mod4, title = "correlation"),
    ggcoefstats(mod5, title = "contingency table", effectsize.type = "cramers_v"),
    ggcoefstats(mod6, title = "anova"),
    ggcoefstats(mod7, title = "regression-1"),
    ggcoefstats(mod8, title = "meta-analysis"),
    ggcoefstats(mod9, title = "proportion test")
  ),
  annotation.args = list(title = "Example from `{BayesFactor}` package")
)
```

--------------------------------

### Generate ggbetweenstats plot

Source: https://indrajeetpatil.github.io/ggstatsplot/reference/ggbetweenstats.html

Generates a plot using the ggbetweenstats function with specified data, grouping, and outcome variables. Includes reproducibility setup.

```R
# for reproducibility
set.seed(123)

p <- ggbetweenstats(mtcars, am, mpg)
p

```

--------------------------------

### Comparative statistical tests with ggwithinstats

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/ggwithinstats.html

Shows how to generate multiple plots using different statistical test types (parametric, nonparametric, robust, and Bayesian) for a subset of data.

```R
## selecting subset of the data
df_disgust <- dplyr::filter(bugs_long, condition %in% c("LDHF", "HDHF"))

## parametric t-test
p1 <- ggwithinstats(
  data = df_disgust,
  x = condition,
  y = desire,
  type = "p",
  effsize.type = "d",
  conf.level = 0.99,
  title = "Parametric test",
  package = "ggsci",
  palette = "nrc_npg"
)

## Mann-Whitney U test (nonparametric test)
p2 <- ggwithinstats(
  data = df_disgust,
  x = condition,
  y = desire,
  xlab = "Condition",
  ylab = "Desire to kill bugs",
  type = "np",
  conf.level = 0.99,
  title = "Non-parametric Test",
  package = "ggsci",
  palette = "uniform_startrek"
)

## robust t-test
p3 <- ggwithinstats(
  data = df_disgust,
  x = condition,
  y = desire,
  xlab = "Condition",
  ylab = "Desire to kill bugs",
  type = "r",
  conf.level = 0.99,
  title = "Robust Test",
  package = "wesanderson",
  palette = "Royal2"
)

## Bayes Factor for parametric t-test
p4 <- ggwithinstats(
  data = df_disgust,
  x = condition,
  y = desire,
  xlab = "Condition",
  ylab = "Desire to kill bugs",
  type = "bayes",
  title = "Bayesian Test",
  package = "ggsci",
  palette = "nrc_npg"
)
```

--------------------------------

### Inspect Titanic Dataset Structure

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/ggpiestats.html

Use dplyr::glimpse to inspect the structure of the original Titanic dataset and the modified Titanic_full dataset used in examples.

```r
# looking at the original data in tabular format
dplyr::glimpse(Titanic)
#>  'table' num [1:4, 1:2, 1:2, 1:2] 0 0 35 0 0 0 17 0 118 154 ...
#>  - attr(*, "dimnames")=List of 4
#>   ..$ Class   : chr [1:4] "1st" "2nd" "3rd" "Crew"
#>   ..$ Sex     : chr [1:2] "Male" "Female"
#>   ..$ Age     : chr [1:2] "Child" "Adult"
#>   ..$ Survived: chr [1:2] "No" "Yes"
```

```r
# looking at the dataset as a tibble or data frame
dplyr::glimpse(Titanic_full)
#> Rows: 2,201
#> Columns: 5
#> $ id       <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18…
#> $ Class    <fct> 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3…
#> $ Sex      <fct> Male, Male, Male, Male, Male, Male, Male, Male, Male, Male, M…
#> $ Age      <fct> Child, Child, Child, Child, Child, Child, Child, Child, Child…
#> $ Survived <fct> No, No, No, No, No, No, No, No, No, No, No, No, No, No, No, N…
```

--------------------------------

### Create statistical plots with ggbetweenstats

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/ggbetweenstats.html

Generates various statistical test visualizations including parametric, non-parametric, robust, and Bayesian tests.

```R
df_year <- dplyr::filter(gapminder::gapminder, year == 2007 | year == 1957)

p1 <- ggbetweenstats(
  data = df_year,
  x = year,
  y = lifeExp,
  xlab = "Year",
  ylab = "Life expectancy",
  # to remove violin plot
  violin.args = list(width = 0),
  type = "p",
  conf.level = 0.99,
  title = "Parametric test",
  package = "ggsci",
  palette = "nrc_npg"
)

p2 <- ggbetweenstats(
  data = df_year,
  x = year,
  y = lifeExp,
  xlab = "Year",
  ylab = "Life expectancy",
  # to remove box plot
  boxplot.args = list(width = 0),
  type = "np",
  conf.level = 0.99,
  title = "Non-parametric Test",
  package = "ggsci",
  palette = "uniform_startrek"
)

p3 <- ggbetweenstats(
  data = df_year,
  x = year,
  y = lifeExp,
  xlab = "Year",
  ylab = "Life expectancy",
  type = "r",
  conf.level = 0.99,
  title = "Robust Test",
  tr = 0.005,
  package = "wesanderson",
  palette = "Royal2",
  digits = 3
)

## Bayes Factor for parametric t-test and boxviolin plot
p4 <- ggbetweenstats(
  data = df_year,
  x = year,
  y = lifeExp,
  xlab = "Year",
  ylab = "Life expectancy",
  type = "bayes",
  violin.args = list(width = 0),
  boxplot.args = list(width = 0),
  point.args = list(alpha = 0),
  title = "Bayesian Test",
  package = "ggsci",
  palette = "nrc_npg"
)
```

--------------------------------

### ggbetweenstats Configuration Arguments

Source: https://indrajeetpatil.github.io/ggstatsplot/reference/grouped_ggbetweenstats.html

Detailed breakdown of arguments used to configure statistical plots in ggbetweenstats.

```APIDOC
## Arguments for ggbetweenstats

### Description
Configuration arguments for customizing the behavior and appearance of statistical plots generated by ggstatsplot.

### Parameters
- **data** (data frame) - Required - A data frame or tibble containing the variables. Must be ungrouped.
- **xlab** (string) - Optional - Label for x-axis variable.
- **ylab** (string) - Optional - Label for y-axis variable.
- **p.adjust.method** (string) - Optional - Method for p-value adjustment (e.g., "holm", "bonferroni", "fdr").
- **pairwise.display** (string) - Optional - Which pairwise comparisons to display ("significant", "non-significant", "all", "none").
- **bf.message** (logical) - Optional - Whether to display Bayes Factor for parametric tests.
- **results.subtitle** (logical) - Optional - Whether to display statistical test results as a subtitle.
- **centrality.plotting** (logical) - Optional - Whether to display central tendency measure.
- **centrality.type** (string) - Optional - Type of centrality parameter ("parametric", "nonparametric", "robust", "bayes").
- **point.args** (list) - Optional - Aesthetic arguments for ggplot2::geom_point().
- **boxplot.args** (list) - Optional - Aesthetic arguments for ggplot2::geom_boxplot().
- **violin.args** (list) - Optional - Aesthetic arguments for ggplot2::geom_violin().
- **ggtheme** (theme) - Optional - A ggplot2 theme to apply to the plot.
```

--------------------------------

### Create a statistical visualization with ggbetweenstats

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/ggstatsplot.html

Generates a plot comparing groups with embedded descriptive and inferential statistical details.

```R
ggbetweenstats(iris, Species, Sepal.Length)
```

--------------------------------

### Turn off Scientific Notation in ggwithinstats

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/faq.html

Control the display of numerical precision in `ggwithinstats` by setting the `digits` argument. This example shows how to display 4 decimal places.

```r
set.seed(123)
library(ggstatsplot)
library(WRS2)

ggwithinstats(
  WineTasting,
  Wine,
  Taste,
  paired = TRUE
)
```

```r
ggwithinstats(
  WineTasting,
  Wine,
  Taste,
  paired = TRUE,
  digits = 4L
)
```

--------------------------------

### Create Within-Subjects Design Plot

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/ggbarstats.html

Use `ggbarstats` with `paired = TRUE` for within-subjects designs. Ensure `paired` is set to TRUE to get accurate results from the McNemar test.

```r
clinical_trial <- tibble::tribble(
  ~SickBefore, ~SickAfter, ~Counts,
  "No", "Yes", 4,
  "Yes", "No", 25,
  "Yes", "Yes", 13,
  "No", "No", 92
)

ggbarstats(
  data = clinical_trial,
  x = SickAfter,
  y = SickBefore,
  counts = Counts,
  paired = TRUE,
  label = "both",
  title = "Results from imaginary clinical trial",
  package = "ggsci",
  palette = "default_ucscgb"
)
```

--------------------------------

### Customizing Plots with ggplot.component and annotation.args

Source: https://indrajeetpatil.github.io/ggstatsplot/reference/grouped_ggbetweenstats.html

Shows how to modify individual plots using the `ggplot.component` argument for y-axis scaling and `annotation.args` for plot titles. This example uses a filtered movies_long dataset.

```R
# modifying individual plots using `ggplot.component` argument
grouped_ggbetweenstats(
  data = filter(
    movies_long,
    genre %in% c("Action", "Comedy"),
    mpaa %in% c("R", "PG")
  ),
  x = genre,
  y = rating,
  grouping.var = mpaa,
  ggplot.component = scale_y_continuous(
    breaks = seq(1, 9, 1),
    limits = (c(1, 9))
  ),
  annotation.args = list(title = "Ratings by genre for different MPAA ratings")
)
#> Scale for y is already present.
#> Adding another scale for y, which will replace the existing scale.
#> Scale for y is already present.
#> Adding another scale for y, which will replace the existing scale.
```

--------------------------------

### Visualize Regression Models with List Outputs

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/ggcoefstats.html

Demonstrates extracting specific components from a list-based model object (like gamm4) to visualize coefficients.

```R
library(gamm4)

# data
dat <- gamSim(1, n = 400, scale = 2)

# now add 20 level random effect `fac'...
dat$fac <- fac <- as.factor(sample(1:20, 400, replace = TRUE))
dat$y <- dat$y + model.matrix(~ fac - 1) %*% rnorm(20) * .5

# model object
br <- gamm4::gamm4(
    formula = y ~ s(x0) + x1 + s(x2),
    data = dat,
    random = ~ (1 | fac)
  )

# looking at the classes of the objects contained in the list
purrr::map(br, class)

combine_plots(
  plotlist = list(
    # first object plot (only parametric terms are shown)
    ggcoefstats(
      x = br$gam,
      title = "generalized additive model (parametric terms)",
      digits = 3
    ),
    # second object plot
    ggcoefstats(
      x = br$mer,
      title = "linear mixed-effects model",
      digits = 3
    )
  ),
  plotgrid.args = list(nrow = 1)
)
```

--------------------------------

### Describing Distribution with datawizard

Source: https://indrajeetpatil.github.io/ggstatsplot/reference/ggbetweenstats.html

Use datawizard::describe_distribution() for parametric, non-parametric, robust, and Bayesian distribution descriptions.

```R
datawizard::describe_distribution()
```

--------------------------------

### Create a correlation matrix with ggcorrmat

Source: https://indrajeetpatil.github.io/ggstatsplot/index.html

Produces a publication-ready correlation matrix with customizable aesthetics.

```R
set.seed(123)

## as a default this function outputs a correlation matrix plot
ggcorrmat(
  data     = ggplot2::msleep,
  colors   = c("#B2182B", "white", "#4D4D4D"),
  title    = "Correlalogram for mammals sleep dataset",
  subtitle = "sleep units: hours; weight units: kilograms"
)
```

--------------------------------

### Advanced grouped_ggbetweenstats usage

Source: https://indrajeetpatil.github.io/ggstatsplot/index.html

Employ grouped_ggbetweenstats to repeat operations across a single grouping variable. This example demonstrates customization of significance arguments, p-value adjustment, palette, package, plot grid, and annotation.

```R
set.seed(123)

grouped_ggbetweenstats(
  data             = dplyr::filter(movies_long, genre %in% c("Action", "Comedy")),
  x                = mpaa,
  y                = length,
  grouping.var     = genre,
  ggsignif.args    = list(textsize = 4, tip_length = 0.01),
  p.adjust.method  = "bonferroni",
  palette          = "default_jama",
  package          = "ggsci",
  plotgrid.args    = list(nrow = 1),
  annotation.args  = list(title = "Differences in movie length by mpaa ratings for different genres")
)
```

--------------------------------

### Combine Plots for Comparison in R

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/principles.html

This R code snippet combines two plots (superposition and juxtaposition) for comparison. It filters the data first and then uses `combine_plots` to arrange them. Ensure `ggplot2` and `ggstatsplot` are installed and loaded.

```r
df <- dplyr::filter(movies_long, genre %in% c("Comedy", "Drama"))

combine_plots(
  plotlist = list(
    # superposition
    ggplot(data = df, mapping = aes(x = length, y = rating, color = genre)) +
      geom_jitter(size = 3, alpha = 0.5) +
      geom_smooth(method = "lm") +
      labs(title = "superposition (recommended in Cleveland's paradigm)") +
      theme_ggstatsplot(),
    # juxtaposition
    grouped_ggscatterstats(
      data = df,
      x = length,
      y = rating,
      grouping.var = genre,
      marginal = FALSE,
      annotation.args = list(title = "juxtaposition (`{ggstatsplot}` implementation in `grouped_` functions)")
    )
  ),
  ## combine for comparison
  annotation.args = list(title = "Two ways to compare different aspects of data"),
  plotgrid.args = list(nrow = 2L)
)
```

--------------------------------

### Creating and Combining ggcorrmat Plots

Source: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/purrr_examples.html

Demonstrates splitting a dataframe and applying ggcorrmat across subsets, followed by combining the results.

```R
## splitting the data frame by cut and creating a list
## let's leave out "fair" cut
## also, to make this fast, let's only use 5% of the sample
cut_list <- ggplot2::diamonds %>%
  dplyr::sample_frac(size = 0.05) %>%
  dplyr::filter(cut != "Fair") %>%
  split(f = .$cut, drop = TRUE)

## checking the length and names of each element
length(cut_list)
names(cut_list)

## running function on every element of this list note that if you want the same
## value for a given argument across all elements of the list, you need to
## specify it just once
plot_list <- purrr::pmap(
  .l = list(
    data = cut_list,
    cor.vars = list(c("carat", "depth", "table", "price")),
    type = list("pearson", "np", "robust", "bf"),
    partial = list(TRUE, FALSE, TRUE, FALSE),
    title = list("Cut: Good", "Cut: Very Good", "Cut: Premium", "Cut: Ideal"),
    p.adjust.method = list("hommel", "fdr", "BY", "hochberg"),
    lab.size = 3.5,
    colors = list(
      c("#56B4E9", "white", "#999999"),
      c("#CC79A7", "white", "#F0E442"),
      c("#56B4E9", "white", "#D55E00"),
      c("#999999", "white", "#0072B2")
    ),
    ggtheme = list(
      ggplot2::theme_linedraw(),
      ggplot2::theme_classic(),
      ggthemes::theme_fivethirtyeight(),
      ggthemes::theme_tufte()
    )
  ),
  .f = ggcorrmat
)

## combining all individual plots from the list into a single plot using
## `combine_plots` function
combine_plots(
  plotlist = plot_list,
  guides = "keep",
  annotation.args = list(
    title = "Relationship between diamond attributes and price across cut",
    caption = "Dataset: Diamonds from ggplot2 package"
  ),
  plotgrid.args = list(nrow = 2L)
)
```

--------------------------------

### Grouped Scatter Plot with Labeling and Secondary Axis

Source: https://indrajeetpatil.github.io/ggstatsplot/reference/grouped_ggscatterstats.html

This example demonstrates using grouped_ggscatterstats with labeling features and modifying the plot by adding a secondary y-axis. It uses the 'mpg' dataset and filters for cylinders not equal to 5.

```R
grouped_ggscatterstats(
  data             = filter(ggplot2::mpg, cyl != 5),
  x                = displ,
  y                = hwy,
  grouping.var     = cyl,
  type             = "robust",
  label.var        = manufacturer,
  label.expression = hwy > 25 & displ > 2.5,
  ggplot.component = scale_y_continuous(sec.axis = dup_axis())
)
```

--------------------------------

### Create Grouped Scatter Plot with Statistics

Source: https://indrajeetpatil.github.io/ggstatsplot/reference/grouped_ggscatterstats.html

Use grouped_ggscatterstats to generate scatter plots with statistical summaries for different groups. This example filters data for 'Comedy' and 'Drama' genres and adds rug plots to the x-axis.

```R
set.seed(123)

library(dplyr, warn.conflicts = FALSE)
library(ggplot2)

grouped_ggscatterstats(
  data             = filter(movies_long, genre == "Comedy" | genre == "Drama"),
  x                = length,
  y                = rating,
  type             = "robust",
  grouping.var     = genre,
  ggplot.component = list(geom_rug(sides = "b"))
)
```
Tokens:
Raw