数据可视化分析中我们经常需要进行数据间的统计分析,并进行显著性标记,虽然ggpur
包被大佬吐槽制造混乱,但在进行显著性标记标记方面也是有其可取之处。
下面主要展示ggpubr
与ggsignif
包对数据进行统计分析,喜欢的小伙伴可以关注我的公众号R语言数据分析指南
将分享更多实用文档,先行拜谢了
加载R包
library(pacman)
pacman::p_load(tidyverse,ggpubr,rstatix,ggsci,ggsignif,reshape2)
wilcox(秩合检验)
ggplot(iris,aes(Species,Sepal.Length,fill=Species)) +
geom_boxplot()+geom_jitter(shape=16,size=2,position=position_jitter(0.2))+
geom_signif(comparisons = list(c("versicolor", "virginica"),
c("versicolor","setosa"),
c("virginica","setosa")),
map_signif_level=T,
textsize=6,test=wilcox.test,step_increase=0.2)+
guides(fill=FALSE)+xlab(NULL)+theme_classic()
t_test分析
ggplot(iris,aes(Species,Sepal.Length,fill=Species)) +
geom_boxplot()+
scale_fill_jco()+
geom_jitter(shape=16,size=2,position=position_jitter(0.2))+
geom_signif(comparisons = list(c("versicolor", "virginica"),
c("versicolor","setosa"),
c("virginica","setosa")),
map_signif_level=T,
textsize=6,test=t.test,step_increase=0.2)+
guides(fill=F)+xlab(NULL)+theme_classic()
anova分析
ggplot(iris,aes(Species,Sepal.Length,fill=Species)) +
geom_boxplot()+
scale_fill_jco()+
geom_jitter(shape=16,size=2,position=position_jitter(0.2))+
stat_compare_means(method = "anova")+theme_bw()
kruskal分析
ggplot(iris,aes(Species,Sepal.Length,fill=Species)) +
geom_boxplot()+
scale_fill_jco()+
geom_jitter(shape=16,size=2,position=position_jitter(0.2))+
stat_compare_means()+theme_bw()
对多组数据进行分面
iris %>% melt() %>%
ggplot(aes(variable,value,fill=Species)) +
geom_boxplot()+
scale_fill_jco()+
stat_compare_means(label = "p.format")+
facet_grid(.~variable,scales = "free",space="free_x")+
theme_bw()+theme(axis.text.x = element_blank())
iris %>% melt() %>%
ggplot(aes(variable,value,fill=Species)) +
geom_boxplot()+
scale_fill_jco()+
stat_compare_means(label = "p.signif", label.x = 1.5)+
facet_grid(.~variable,scales = "free",space="free_x")+
theme_bw()+theme(axis.text.x = element_blank())