# `ggstatsplot`介绍

`ggstatsplot``ggplot2`包的扩展，主要用于创建美观的图片同时自动输出统计学分析结果，其统计学分析结果包含统计分析的详细信息，该包对于经常需要做统计分析的科研工作者来说非常有用。

`ggstatsplot`在统计学分析方面：目前它支持最常见的统计测试类型：t-test / anova，非参数，相关性分析，列联表分析和回归分析。而在图片输出方面：（1）小提琴图（用于不同组之间连续数据的异同分析）；（2）饼图（用于分类数据的分布检验）；（3）条形图（用于分类数据的分布检验）；（4）散点图（用于两个变量之间的相关性分析）；（5）相关矩阵（用于多个变量之间的相关性分析）；（6）直方图和点图/图表（关于分布的假设检验）；（7）点须图（用于回归模型）。

# ggbetweenstats函数

``````# loading needed libraries
library(ggstatsplot)

# for reproducibility
set.seed(123)

# plot
ggstatsplot::ggbetweenstats(
data = iris,
x = Species,
y = Sepal.Length,
messages = FALSE
) + # further modification outside of ggstatsplot
ggplot2::coord_cartesian(ylim = c(3, 8)) +
ggplot2::scale_y_continuous(breaks = seq(3, 8, by = 1))
``````

``````library(ggplot2)
# for reproducibility
set.seed(123)
# let's leave out one of the factor levels and see if instead of anova, a t-test will be run
iris2 <- dplyr::filter(.data = iris, Species != "setosa")
# let's change the levels of our factors, a common routine in data analysis
# pipeline, to see if this function respects the new factor levels
iris2\$Species <-
base::factor(
x = iris2\$Species,
levels = c("virginica", "versicolor")
)
# plot
ggstatsplot::ggbetweenstats(
data = iris2,
x = Species,
y = Sepal.Length,
notch = TRUE, # show notched box plot
mean.plotting = TRUE, # whether mean for each group is to be displayed
mean.ci = TRUE, # whether to display confidence interval for means
mean.label.size = 2.5, # size of the label for mean
type = "p", # which type of test is to be run
k = 3, # number of decimal places for statistical results
outlier.tagging = TRUE, # whether outliers need to be tagged
outlier.label = Sepal.Width, # variable to be used for the outlier tag
outlier.label.color = "darkgreen", # changing the color for the text label
xlab = "Type of Species", # label for the x-axis variable
ylab = "Attribute: Sepal Length", # label for the y-axis variable
title = "Dataset: Iris flower data set", # title text for the plot
ggtheme = ggthemes::theme_fivethirtyeight(), # choosing a different theme
ggstatsplot.layer = FALSE, # turn off ggstatsplot theme layer
package = "wesanderson", # package from which color palette is to be taken
palette = "Darjeeling1", # choosing a different color palette
messages = FALSE
)
``````

# ggbetweenstats函数

ggbetweenstats函数的功能几乎与ggwithinstats相同。

``````# for reproducibility and data
set.seed(123)
data("iris")
ggstatsplot::ggwithinstats(
data = iris,
x = Species,
y = Sepal.Length,
messages = FALSE
)
``````
``````# plot
ggstatsplot::ggwithinstats(
data = iris,
x = Species,
y = Sepal.Length,
sort = "descending", # ordering groups along the x-axis based on
sort.fun = median, # values of `y` variable
pairwise.comparisons = TRUE,
pairwise.display = "s",
pairwise.annotation = "p",
title = "iris",
caption = "Data from: iris",
ggtheme = ggthemes::theme_fivethirtyeight(),
ggstatsplot.layer = FALSE,
messages = FALSE
)
``````

# ggscatterstats函数

``````ggstatsplot::ggscatterstats(
data = ggplot2::msleep,
x = sleep_rem,
y = awake,
xlab = "REM sleep (in hours)",
ylab = "Amount of time spent awake (in hours)",
title = "Understanding mammalian sleep",
messages = FALSE
)
``````

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

# plot
ggstatsplot::ggscatterstats(
data = dplyr::filter(.data = ggstatsplot::movies_long, genre == "Action"),
x = budget,
y = rating,
type = "robust", # type of test that needs to be run
conf.level = 0.99, # confidence level
xlab = "Movie budget (in million/ US\$)", # label for x axis
ylab = "IMDB rating", # label for y axis
label.var = "title", # variable for labeling data points
label.expression = "rating < 5 & budget > 100", # expression that decides which points to label
line.color = "yellow", # changing regression line color line
title = "Movie budget and IMDB rating (action)", # title text for the plot
caption = expression( # caption text for the plot
paste(italic("Note"), ": IMDB stands for Internet Movie DataBase")
),
ggtheme = theme_bw(), # choosing a different theme
ggstatsplot.layer = FALSE, # turn off ggstatsplot theme layer
marginal.type = "density", # type of marginal distribution to be displayed
xfill = "#0072B2", # color fill for x-axis marginal distribution
yfill = "#009E73", # color fill for y-axis marginal distribution
xalpha = 0.6, # transparency for x-axis marginal distribution
yalpha = 0.6, # transparency for y-axis marginal distribution
centrality.para = "median", # central tendency lines to be displayed
messages = FALSE # turn off messages and notes
)

``````

# ggbarstats柱状图

ggbarstats函数主要用于展示不同组之间分类数据的分布问题。比如说说A组患者中，男女的比例是否与B组患者中男女的比例存在异同。

``````# for reproducibility
set.seed(123)
# plot
ggstatsplot::ggbarstats(
data = ggstatsplot::movies_long,
main = mpaa,
condition = genre,
sampling.plan = "jointMulti",
title = "MPAA Ratings by Genre",
xlab = "movie genre",
perc.k = 1,
x.axis.orientation = "slant",
ggtheme = hrbrthemes::theme_modern_rc(),
ggstatsplot.layer = FALSE,
ggplot.component = ggplot2::theme(axis.text.x = ggplot2::element_text(face = "italic")),
palette = "Set2",
messages = FALSE
)
``````

# gghistostats

``````ggstatsplot::gghistostats(
data = ToothGrowth, # dataframe from which variable is to be taken
x = len, # numeric variable whose distribution is of interest
title = "Distribution of Sepal.Length", # title for the plot
test.value = 10, # the comparison value for t-test
test.value.line = TRUE, # display a vertical line at test value
type = "bf", # bayes factor for one sample t-test
bf.prior = 0.8, # prior width for calculating the bayes factor
messages = FALSE # turn off the messages
)
``````

# ggdotplotstats

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

# plot
ggdotplotstats(
data = dplyr::filter(.data = gapminder::gapminder, continent == "Asia"),
y = country,
x = lifeExp,
test.value = 55,
test.value.line = TRUE,
test.line.labeller = TRUE,
test.value.color = "red",
centrality.para = "median",
centrality.k = 0,
title = "Distribution of life expectancy in Asian continent",
xlab = "Life expectancy",
messages = FALSE,
caption = substitute(
paste(
italic("Source"),
": Gapminder dataset from https://www.gapminder.org/"
)
)
)

``````

# ggcorrmat

ggcorrmat函数主要用于变量之间的相关性分析

``````# for reproducibility
set.seed(123)
# as a default this function outputs a correlalogram plot
ggstatsplot::ggcorrmat(
data = ggplot2::msleep,
corr.method = "robust", # correlation method
sig.level = 0.001, # threshold of significance
cor.vars = c(sleep_rem, awake:bodywt), # a range of variables can be selected
cor.vars.names = c(
"REM sleep", # variable names
"time awake",
"brain weight",
"body weight"
),
matrix.type = "upper", # type of visualization matrix
colors = c("#B2182B", "white", "#4D4D4D"),
title = "Correlalogram for mammals sleep dataset",
subtitle = "sleep units: hours; weight units: kilograms"
)
``````

# ggcoefstats

ggcoefstats创建了很多回归系数的点估计值作为带有置信区间的点。

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

# model
mod <- stats::lm(
formula = mpg ~ am * cyl,
data = mtcars
)

# plot
ggstatsplot::ggcoefstats(x = mod)
``````

# 用其他包绘图，同时用ggstatsplot包展示统计分析结果

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

library(yarrr)
library(ggstatsplot)

# using `ggstatsplot` to get call with statistical results
stats_results <-
ggstatsplot::ggbetweenstats(
data = ChickWeight,
x = Time,
y = weight,
return = "subtitle",
messages = FALSE
)
# using `yarrr` to create plot
yarrr::pirateplot(
formula = weight ~ Time,
data = ChickWeight,
theme = 1,
main = stats_results
)
``````