如何将统计测试的结果作为绘图表达式包含在 ggplot2 方面

Question

我希望在多面 ggplot 图表中包含多个统计测试的结果。

我找到了很多关于如何在标题或注释中包含类似内容的优秀示例（如this ），但是，我的兴趣在于将其作为文本注释包含在内，以便我可以在一个图形上显示许多测试的结果。

我已经能够使用标准文本注释来做到这一点，但是我想使用polymath / expressions来呈现我的结果，以便我可以生成遵循 package [ggstatsplot] 1中实现的 APA 样式指南的注释，请参见下面的示例：

我使用来自ggplot2的diamonds数据包含了一个可重现示例的代码。 我尝试过的一些事情包括：

• 试图将bquote和expression对象存储为wilcox_stats object 中的列 - 但是 dplyr 似乎不喜欢它
• 试图从ggplot调用这一切——但是尝试排除geom_text想要打印的所有注释变得非常混乱

您可以提供的任何帮助或指示将不胜感激。

# LOAD REQUIRED PACKAGES

library(ggplot2)
library(tidyverse)
library(rstatix)

# CREATE SAMPLE DATA

sample_data <- diamonds %>%
  select(cut, color, table) %>%
  filter(color == c("E","J")) %>%
  mutate(time = factor(case_when(
    table %% 2 == 0 ~ "Before",
    TRUE ~ "After"))) %>%
  group_by(color, time) %>%
  sample_n(100) %>%
  ungroup() %>%
  mutate(numeric_cut = case_when(
    cut == "Ideal" ~ 1, 
    cut == "Premium" ~ 2,     
    cut == "Very Good" ~ 3,
    cut == "Good" ~ 4,
    cut == "Fair" ~ 5))

# STAT TESTS

wilcox_test <- sample_data %>%
  group_by(color) %>%
  wilcox_test(numeric_cut ~ time, paired = TRUE, detailed = TRUE) %>%
  select(color, statistic, p, n1)

wilcox_es <- sample_data %>%
  group_by(color) %>%
  wilcox_effsize(numeric_cut ~ time, paired = TRUE, ci = TRUE) %>%
  select(color, effsize, conf.low, conf.high)

## EXTRACT ELEMENTS OF STAT TESTS AND USE THEM TO CREATE ANNOTATION

wilcox_stats <- left_join(wilcox_test, wilcox_es) %>%
  mutate(statistic = round(statistic, 1)) %>%
  mutate(effsize = round(effsize, 2)) %>%
  mutate(p = round(p, 3)) %>%
  mutate(result = deparse(bquote(
    V[Wilcoxon]==.(statistic)~ #this code does not work
    italics(p)==.p~ 
    hat(r) == .effsize~
    "CI"["95%"]~
    .conf.low~.conf.high~
    n[pairs]==.n1)))

## PREPARE PLOT DATA

plot_data <- sample_data %>%
  group_by(time, cut, color) %>%
  tally() %>%
  ungroup() %>%
  group_by(color) %>%
  mutate(total_n = sum(n)) %>%
  mutate(percent = (n/total_n)*100) %>%
  mutate(percent = round(percent, 1)) %>%
  ungroup() %>%
  left_join(wilcox_stats) %>%
  mutate(result = case_when(
    time == "Before" & cut == "Ideal" ~ "",
    time == "After" & cut == "Ideal" ~ "",
    time == "Before" & cut == "Premium" ~ "",
    time == "After" & cut == "Premium" ~ "",
    time == "Before" & cut == "Very Good" ~ "",
    time == "After" & cut == "Very Good" ~ result,
    time == "Before" & cut == "Good" ~ "",
    time == "After" & cut == "Good" ~ "",
    time == "Before" & cut == "Fair" ~ "",
    time == "After" & cut == "Fair" ~ "")) %>%
  mutate(time = factor(time, levels = c("Before", "After", ordered = TRUE)))

## PLOT RESULTS

plot <- plot_data %>%
  ggplot() +
  aes(x = cut, y = percent, fill = cut) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = result, y = 30), size = 5, parse = TRUE) +
  facet_grid(color ~ time)

下图显示了我希望创建的 output 的要点...

Answer 1

我可能会使用粘贴创建表达式，（tbh，因为我发现包含变量更容易）。

我稍微缩短了代码，也没有使用你的完整表达，但我认为它应该足以让你明白这一点。

library(tidyverse)

sample_data <- diamonds %>%
  select(cut, color, table) %>%
  filter(color == c("E","J")) %>%
  mutate(time = if_else(table %% 2 == 0, "Before", "After")) %>%
  group_by(color, time) %>%
  sample_n(100) %>%
  ungroup() %>%
  mutate(numeric_cut = as.numeric(cut))

wilcox_test <- sample_data %>%
  group_by(color) %>%
  rstatix::wilcox_test(numeric_cut ~ time, paired = TRUE, detailed = TRUE) %>%
  select(color, statistic, p, n1)

wilcox_es <- sample_data %>%
  group_by(color) %>%
  rstatix::wilcox_effsize(numeric_cut ~ time, paired = TRUE, ci = TRUE) %>%
  select(color, effsize, conf.low, conf.high)

这里是关键点

wilcox_stats <- left_join(wilcox_test, wilcox_es) %>%
  mutate(statistic = round(statistic, 1),
         effsize = round(effsize, 2),
         p = round(p, 3),
         label = paste('V[Wilcoxon]==', statistic, '~italic(p)==~', p))
#> Joining, by = "color"

plot_data <- sample_data %>%
  count(time, cut, color) %>%
  group_by(color) %>%
  mutate(total_n = sum(n),
         percent = round((n/total_n)*100,1)) %>%
  ungroup() %>%
  left_join(wilcox_stats) %>%
  mutate(result = if_else(time == "After" & cut == "Very Good", label, ""))
#> Joining, by = "color"

plot_data %>%
  ggplot() +
  aes(x = cut, y = percent, fill = cut) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = result, y = 30), parse = TRUE) +
  facet_grid(color ~ time)

^{由代表 package (v0.3.0) 于 2020 年 4 月 26 日创建}