代码之家 › 专栏 › 技术社区 › Eric Green

在给定的x轴值处添加在不同回归线上的点之间延伸的垂直线段

ggplot2 r

0

Eric Green · 技术社区 · 3 年前

我想在 days==0 从 y 哪里 天数==0 在…之间 x==0 ,到值 y 哪里 天数==0 在…之间 x==1 。

df <- structure(list(y = c(3, 4, 4, 3, 4, 4, 4, 3, 4, 4, 4, 3, 4, 4, 
4, 3, 3, 4, 3, 3, 4, 4, 4, 3, 4, 3, 3, 4, 4, 3, 4, 5, 4, 4, 4, 
5, 4, 5, 4, 4, 5, 4, 4, 5, 4, 4, 5, 4, 4, 4, 5, 5, 4, 4, 4, 4, 
5, 5, 5, 4, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 
5, 4, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 7, 6, 6, 6, 7, 
6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 
6), x = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("0", 
"1"), class = "factor"), days = c(-8, -50, -84, -91, -69, -87, 
-89, -19, -61, -18, -46, -26, -35, -51, -88, -55, -36, -44, -24, 
-45, -78, -41, -38, -81, -74, -22, -82, -86, -39, -64, -66, -58, 
-25, -5, -29, -34, -30, -75, -57, -37, -32, -77, -31, -59, -67, 
-83, -70, -1, -65, -15, -27, -56, -71, -80, -12, -3, -76, -54, 
-52, -6, 35, 20, 53, 61, 43, 71, 88, 31, 17, 85, 21, 25, 16, 
46, 45, 41, 15, 48, 72, 63, 24, 12, 83, 40, 13, 10, 11, 79, 81, 
64, 38, 59, 3, 77, 39, 26, 68, 49, 87, 69, 75, 33, 34, 76, 78, 
86, 14, 36, 0, 44, 54, 58, 18, 80, 82, 89, 56, 2, 28, 74)), row.names = c(NA, 
-120L), class = c("tbl_df", "tbl", "data.frame"))

# https://evalf20.classes.andrewheiss.com/example/rdd/
library(tidyverse)

df %>%
  ggplot(aes(x = days, y = y, color = x)) +
    geom_point(size = 2, alpha = 0.5, position = position_jitter(seed = 42)) + 
    geom_smooth(data = filter(df, days < 0), method = "lm") +
    geom_smooth(data = filter(df, days >= 0), method = "lm") +
    geom_vline(xintercept = 0) + 
    labs(x = "Days from cutoff", y = "Outcome") + 
    guides(color = FALSE)

每条线的斜率可能不同,因此我们不能假设 y 在 天数==0 在…之间 x==0 (左)总是在 y 如图所示。

1 回复 | 直到 3 年前

1

4

M-- 3 年前

您可以提取 geom_smooth 回归线,并将它们作为 geom_segment :

library(tidyverse)

df %>%
  ggplot(aes(x = days, y = y, color = x)) +
  geom_point(size = 2, alpha = 0.5, position = position_jitter(seed = 42)) + 
  geom_smooth(data = filter(df, days < 0), method = "lm") +
  geom_smooth(data = filter(df, days >= 0), method = "lm") +
  geom_vline(xintercept = 0) + 
  labs(x = "Days from cutoff", y = "Outcome") + 
  guides(color = "none") -> gg


lm(y~days, data = filter(df, days < 0))-> lm_neg
lm(y~days, data = filter(df, days >= 0))-> lm_pos



gg + 
  geom_segment(aes(x = 0, y = lm_neg$coefficients[1], 
                   xend = 0, yend = lm_pos$coefficients[1]), 
               colour = "yellow", size = 2)

2

3

Ric 3 年前

df <- structure(list(y = c(3, 4, 4, 3, 4, 4, 4, 3, 4, 4, 4, 3, 4, 4, 
4, 3, 3, 4, 3, 3, 4, 4, 4, 3, 4, 3, 3, 4, 4, 3, 4, 5, 4, 4, 4, 
5, 4, 5, 4, 4, 5, 4, 4, 5, 4, 4, 5, 4, 4, 4, 5, 5, 4, 4, 4, 4, 
5, 5, 5, 4, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 
5, 4, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 7, 6, 6, 6, 7, 
6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 
6), x = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("0", 
"1"), class = "factor"), days = c(-8, -50, -84, -91, -69, -87, 
-89, -19, -61, -18, -46, -26, -35, -51, -88, -55, -36, -44, -24, 
-45, -78, -41, -38, -81, -74, -22, -82, -86, -39, -64, -66, -58, 
-25, -5, -29, -34, -30, -75, -57, -37, -32, -77, -31, -59, -67, 
-83, -70, -1, -65, -15, -27, -56, -71, -80, -12, -3, -76, -54, 
-52, -6, 35, 20, 53, 61, 43, 71, 88, 31, 17, 85, 21, 25, 16, 
46, 45, 41, 15, 48, 72, 63, 24, 12, 83, 40, 13, 10, 11, 79, 81, 
64, 38, 59, 3, 77, 39, 26, 68, 49, 87, 69, 75, 33, 34, 76, 78, 
86, 14, 36, 0, 44, 54, 58, 18, 80, 82, 89, 56, 2, 28, 74)), row.names = c(NA, 
-120L), class = c("tbl_df", "tbl", "data.frame"))

# https://evalf20.classes.andrewheiss.com/example/rdd/


library(tidyverse)

y1 = predict(lm(y ~ days, filter(df, days < 0)), list(days=0))
y2 = predict(lm(y ~ days, filter(df, days >= 0)), list(days=0))

df %>%
  ggplot(aes(x = days, y = y, color = x)) +
    geom_point(size = 2, alpha = 0.5, position = position_jitter(seed = 42)) + 
    geom_smooth(data = filter(df, days < 0), method = "lm") +
    geom_smooth(data = filter(df, days >= 0), method = "lm") +
    geom_vline(xintercept = 0) + 
    labs(x = "Days from cutoff", y = "Outcome") + 
    guides(color = FALSE) + 
  annotate("segment", x=0,xend=0, y=y1, yend=y2  , color = "yellow", size = 3)

^{创建于2023-01-16

reprex v2.0.2}