r - 是否有一种巧妙的方法可以使用来自 geom_quantile() 的方程和其他统计数据来标记 ggplot 图？

Question

我想以与 geom_smooth(method="lm") 类似的方式包含来自 geom_quantile() 拟合线的相关统计数据> 拟合线性回归(我之前使用的是 ggpmisc，即 awesome)。例如，这段代码:

# quantile regression example with ggpmisc equation
# basic quantile code from here:
# https://ggplot2.tidyverse.org/reference/geom_quantile.html

library(tidyverse)
library(ggpmisc)
# see ggpmisc vignette for stat_poly_eq() code below:
# https://cran.r-project.org/web/packages/ggpmisc/vignettes/user-guide.html#stat_poly_eq

my_formula <- y ~ x
#my_formula <- y ~ poly(x, 3, raw = TRUE)

# linear ols regression with equation labelled
m <- ggplot(mpg, aes(displ, 1 / hwy)) +
  geom_point()

m + 
  geom_smooth(method = "lm", formula = my_formula) +
  stat_poly_eq(aes(label =  paste(stat(eq.label), "*\" with \"*", 
                                  stat(rr.label), "*\", \"*", 
                                  stat(f.value.label), "*\", and \"*",
                                  stat(p.value.label), "*\".\"",
                                  sep = "")),
               formula = my_formula, parse = TRUE, size = 3)  

生成这个:

对于分位数回归，您可以将 geom_smooth() 换成 geom_quantile() 并绘制一条可爱的分位数回归线(在本例中为中位数):

# quantile regression - no equation labelling
m + 
  geom_quantile(quantiles = 0.5)
  

您如何将摘要统计数据输出到标签中，或者在移动中重新创建它们？ (即除了在调用 ggplot 之前进行回归然后将其传递给然后注释(例如类似于为线性回归所做的 here 或 here？

Answer 1

请将此视为 Pedro 出色回答的附录，他在其中完成了大部分繁重的工作 - 这增加了一些演示调整(颜色和线型)和代码以简化多个分位数，生成如下图:

library(tidyverse)
library(ggpmisc) #ensure version 0.3.8 or greater
library(quantreg)
library(generics)

my_formula <- y ~ x
#my_formula <- y ~ poly(x, 3, raw = TRUE)

# base plot
m <- ggplot(mpg, aes(displ, 1 / hwy)) +
  geom_point()

# function for labelling
# Doesn't neatly handle P values (e.g return "P<0.001 where appropriate)

stat_rq_eqn <- function(formula = y ~ x, tau = 0.5, colour = "red", label.y = 0.9, ...) {
  stat_fit_tidy(method = "rq",
                method.args = list(formula = formula, tau = tau), 
                tidy.args = list(se.type = "nid"),
                mapping = aes(label = sprintf('italic(tau)~"="~%.3f~";"~y~"="~%.3g~+~%.3g~x*", with "~italic(P)~"="~%.3g',
                                              after_stat(x_tau),
                                              after_stat(Intercept_estimate), 
                                              after_stat(x_estimate),
                                              after_stat(x_p.value))),
                parse = TRUE,
                colour = colour,
                label.y = label.y,
                ...)
}

# This works, though with double entry of plot specs
# custom colours and linetype
# https://stackoverflow.com/a/44383810/4927395
# https://stackoverflow.com/a/64518380/4927395


m + 
  geom_quantile(quantiles = c(0.1, 0.5, 0.9), 
                aes(colour = as.factor(..quantile..),
                    linetype = as.factor(..quantile..))
                )+
  scale_color_manual(values = c("red","purple","darkgreen"))+
  scale_linetype_manual(values = c("dotted", "dashed", "solid"))+
  stat_rq_eqn(tau = 0.1, colour = "red", label.y = 0.9)+
  stat_rq_eqn(tau = 0.5, colour = "purple", label.y = 0.95)+
  stat_rq_eqn(tau = 0.9, colour = "darkgreen", label.y = 1.0)+
  theme(legend.position = "none") # suppress legend


# not a good habit to have double entry above
# modified with reference to tibble for plot specs, 
# though still a stat_rq_eqn call for each quantile and manual vertical placement
# https://www.r-bloggers.com/2019/06/curly-curly-the-successor-of-bang-bang/

my_tau = c(0.1, 0.5, 0.9)
my_colours = c("red","purple","darkgreen")
my_linetype = c("dotted", "dashed", "solid")

quantile_plot_specs <- tibble(my_tau, my_colours, my_linetype)

m + 
  geom_quantile(quantiles = {{quantile_plot_specs$my_tau}}, 
                aes(colour = as.factor(..quantile..),
                    linetype = as.factor(..quantile..))
  )+
  scale_color_manual(values = {{quantile_plot_specs$my_colours}})+
  scale_linetype_manual(values = {{quantile_plot_specs$my_linetype}})+
  stat_rq_eqn(tau = {{quantile_plot_specs$my_tau[1]}}, colour = {{quantile_plot_specs$my_colours[1]}}, label.y = 0.9)+
  stat_rq_eqn(tau = {{quantile_plot_specs$my_tau[2]}}, colour = {{quantile_plot_specs$my_colours[2]}}, label.y = 0.95)+
  stat_rq_eqn(tau = {{quantile_plot_specs$my_tau[3]}}, colour = {{quantile_plot_specs$my_colours[3]}}, label.y = 1.0)+
  theme(legend.position = "none")