20210122

library(tidyverse)

## ── Attaching packages ────────────────────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.2     ✓ purrr   0.3.4
## ✓ tibble  3.0.4     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.0

## ── Conflicts ───────────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(ggpubr)
library(rstatix)

## 
## Attaching package: 'rstatix'

## The following object is masked from 'package:stats':
## 
##     filter

library(readxl)
options(scipen = 15)

1 基礎統計量と箱ひげ図

dat1 <- read_excel("/Users/riku/desktop/0122.xlsx")
dat1$Group <- as.factor(dat1$Group)

dat1 %>% 
  group_by(Group) %>%
  get_summary_stats(Score, type = "common")

ggboxplot(dat1, x = "Group", y = "Score")

2 外れ値

dat1 %>% 
  group_by(Group) %>%
  identify_outliers(Score)

3 正規性検定

D、E、Fは正規分布に従わないので、Kruskal-Wallis Testを使います。

dat1 %>%
  group_by(Group) %>%
  shapiro_test(Score)

4 Kruskal-Wallis Test

群間の差が有意

res.kruskal <- dat1 %>% kruskal_test(Score ~ Group)
res.kruskal

5 Effict size

効果量が大

dat1 %>% kruskal_effsize(Score ~ Group)

6 Pairwise comparisons

#Dun法で多重比較する場合
pwc <- dat1 %>% 
  dunn_test(Score ~ Group, p.adjust.method = "bonferroni") 
pwc

#wilcos_testで多重比較する場合
pwc2 <- dat1 %>% 
  wilcox_test(Score ~ Group, p.adjust.method = "bonferroni") 
pwc2

7 結果

pwc <- pwc %>% add_xy_position(x = "Group")
ggboxplot(dat1, x = "Group", y = "Score") +
  stat_pvalue_manual(pwc, hide.ns = TRUE) +
  labs(
    subtitle = get_test_label(res.kruskal, detailed = TRUE),
    caption = get_pwc_label(pwc)
    )