創建具有均值和置信區間的 ggplot

Question

我創建了一個圖表，其中包含每個人的曲線和以相同方式創建的平均曲線。 我想在我的平均曲線上有一個置信區間。 我怎樣才能做到這一點？ 是否應該以不同的方式創建平均曲線？ 到目前為止，這是我的代碼：

DNAMorfR %>%
  drop_na(`Normal morphology (%)`) %>%
  ggplot(aes(x = Time, y = `Normal morphology (%)`, linetype = Patient, color = Patient, group 
= Patient, na.rm = TRUE)) +
  geom_line(size = 1) +
  theme_minimal() + ggtitle("(A1) Normal morphology") +
  geom_point(size = 1.5) +
  scale_y_continuous(limits = c(0, 25), breaks=seq(0, 25, by = 5)) +
  geom_hline(yintercept = 4, color = "grey", size = 1) +
  scale_color_manual(values = c("black", "#FF3333", "#FF9933", "#CC9900"))

這是我的數據：

data.frame(
stringsAsFactors = FALSE,
check.names = FALSE,
Patient = c("1","1","1","2","2","2","3","3","3","mean","mean","mean"),
`Normal morphology (%)` = c(7, 2, 3, 1, 3, 3, 6, 7, 8, 7, 9, 8),
Time = as.factor(c("Week 1","Week 2","Week 3","Week 1","Week 2","Week 3","Week 1","Week 2",
"Week 3","Week 1","Week 2","Week 3")))

Answer 1

這可以像這樣實現：

1. 您可以使用例如dplyr::summarize來制作摘要 df，而不是將平均值添加為附加行
2. 就像我在下面的方法中所做的那樣，使用stat_summay計算匯總統計數據，並將置信區間計算為mean(x) +/- 1.96 / (length(x) - 1) * sd(x)

library(ggplot2)
library(tidyr)
library(dplyr)

DNAMorfR1 <- DNAMorfR %>%
  drop_na(`Normal morphology (%)`) %>% 
  filter(Patient != "mean")

ggplot(DNAMorfR1, aes(x = Time, y = `Normal morphology (%)`)) +
  geom_line(aes(linetype = Patient, color = Patient, group = Patient), size = 1) +
  geom_point(aes(color = Patient, group = Patient), size = 1.5) +
  stat_summary(aes(color = "mean", linetype = "mean", group = "mean"), geom = "line", fun = "mean") +
  stat_summary(aes(color = "mean", group = "mean"), geom = "pointrange", fun = "mean", 
               fun.min = function(x) mean(x) - 1.96 / (length(x) - 1) * sd(x), 
               fun.max = function(x) mean(x) + 1.96 / (length(x) - 1) * sd(x), show.legend = FALSE) +
  theme_minimal() + 
  ggtitle("(A1) Normal morphology") +
  scale_y_continuous(limits = c(0, 25), breaks=seq(0, 25, by = 5)) +
  geom_hline(yintercept = 4, color = "grey", size = 1) +
  scale_color_manual(values = c("black", "#FF3333", "#FF9933", "#CC9900"))

Answer 2

您可以使用geom = "ribbon"將 95% CI 帶置於您的平均線。 感謝 stefan，其中主要邏輯已經得到解答！

DNAMorfR %>%
  drop_na(`Normal morphology (%)`) %>%
  filter(row_number() <= n()-3) %>% 
  ggplot(aes(x = Time, y = `Normal morphology (%)`)) +
  geom_line(aes(linetype = Patient, color = Patient, group = Patient), size = 1) +
  geom_point(aes(color = Patient, group = Patient), size = 2) +
  stat_summary(aes(color = "mean", linetype = "mean", group = "mean"), size=1.5, geom = "line", fun = "mean") +
  stat_summary(aes(color = "mean", group = "mean"), geom = "ribbon", fun = "mean", size= 0.5, alpha=0.1,
               fun.min = function(x) mean(x) - 1.96 / (length(x) - 1) * sd(x), 
               fun.max = function(x) mean(x) + 1.96 / (length(x) - 1) * sd(x), show.legend = FALSE) +
  theme_minimal() + 
  ggtitle("(A1) Normal morphology") +
  scale_y_continuous(limits = c(0, 25), breaks=seq(0, 25, by = 5)) +
  geom_hline(yintercept = 4, color = "grey", size = 1) +
  scale_color_manual(values = c("black", "#FF3333", "#FF9933", "#CC9900"))