split vilon plot with overly crude and adjusted estimates from linear regression

Question

I want to create a split vilon plot for comparing distance and age and overly crude and adjusted estimates from linear regression on it. my outcome variable lung function. any help would be really appreciated

structure(list(id = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 11L, 12L, 13L, 

14L, 15L, 16L, 17L, 21L, 22L, 23L, 24L, 25L, 26L, 27L, 31L, 32L, 33L, 34L, 35L, 36L, 37L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 51L, 52L, 53L, 54L, 55L, 56L, 57L, 61L, 62L, 63L, 64L, 65L, 66L, 67L ), age = c("child", "child", "adult", "child", "adult", "adult", "adult", "child", "child", "adult", "child", "adult", "adult", "adult", "child", "child", "adult", "child", "adult", "adult", "adult", "child", "child", "adult", "child", "adult", "adult", "adult", "child", "child", "adult", "child", "adult", "adult", "adult", "child", "child", "adult", "child", "adult", "adult", "adult", "child", "child", "adult", "child", "adult", "adult", "adult"), sex = c("M", "F", "M", "M", "M", "F", "F", "F", "M", "M", "M", "F", "F", "F", "M", "M", "M", "F", "F", "F", "F", "M", "M", "F", "F", "F", "F", "M", "M", "F", "F", "F", "F", "M", "F", "F", "F", "F", "F", "M", "F", "M", "F", "F", "F", "M", "F", "M", "M"), distance = c("a", "a", "a", "a", "b", "b", "b", "a", "a", "a", "a", "b", "b", "b", "a", "a", "a", "a", "b", "b", "b", "a", "a", "a", "b", "b", "b", "b", "b", "b", "a", "b", "b", "b", "b", "b", "b", "a", "b", "b", "b", "b", "b", "b", "a", "b", "b", "b", "b"), edu = c("x", "x", "x", "y", "y", "y", "z", "x", "x", "x", "y", "y", "y", "z", "x", "x", "x", "y", "y", "y", "z", "x", "x", "x", "y", "y", "y", "z", "x", "x", "x", "y", "y", "y", "z", "x", "x", "x", "y", "y", "y", "z", "x", "x", "x", "y", "y", "y", "z" ), lungfunction = c(45L, 23L, 25L, 45L, 70L, 69L, 90L, 23L, 25L, 45L, 70L, 69L, 90L, 50L, 25L, 45L, 70L, 69L, 90L, 50L, 62L, 45L, 70L, 69L, 90L, 50L, 62L, 45L, 70L, 69L, 90L, 50L, 62L, 45L, 23L, 69L, 90L, 50L, 62L, 45L, 23L, 25L, 90L, 50L, 62L, 45L, 23L, 25L, 45L), no2 = c(40L, 70L, 50L, 60L, 30L, 25L, 80L, 70L, 50L, 60L, 30L, 25L, 80L, 89L, 50L, 60L, 30L, 25L, 80L, 89L, 10L, 60L, 30L, 25L, 80L, 89L, 10L, 40L, 30L, 25L, 80L, 89L, 10L, 40L, 70L, 25L, 80L, 89L, 10L, 40L, 70L, 50L, 80L, 89L, 10L, 40L, 70L, 50L, 60L ), pm25 = c(15L, 20L, 36L, 48L, 25L, 36L, 28L, 20L, 36L, 48L, 25L, 36L, 28L, 15L, 36L, 48L, 25L, 36L, 28L, 15L, 25L, 48L, 25L, 36L, 28L, 15L, 25L, 15L, 25L, 36L, 28L, 15L, 25L, 15L, 20L, 36L, 28L, 15L, 25L, 15L, 20L, 36L, 28L, 15L, 25L, 15L, 20L, 36L, 48L )), row.names = c(NA, -49L), class = "data.frame")

crude <- lm(lungfunction~distance, data = publication_dummytable2) summary(crude)

adjusted <- lm(lungfunction~distance+age+edu+no2+pm25, data = publication_dummytable2) summary(adjusted)

Answer 1

It is not clear in the question of what columns belong to crude and adjusted values. Here is something using no2 and pm25:

library(tidyverse)
library(ggh4x)
library(see)

data <- structure(list(id = c(
  1L, 2L, 3L, 4L, 5L, 6L, 7L, 11L, 12L, 13L,
  14L, 15L, 16L, 17L, 21L, 22L, 23L, 24L, 25L, 26L, 27L, 31L, 32L,
  33L, 34L, 35L, 36L, 37L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 51L,
  52L, 53L, 54L, 55L, 56L, 57L, 61L, 62L, 63L, 64L, 65L, 66L, 67L
), age = c(
  "a", "a", "b", "a", "b", "b", "b", "a", "a", "b",
  "a", "b", "b", "b", "a", "a", "b", "a", "b", "b", "b", "a", "a",
  "b", "a", "b", "b", "b", "a", "a", "b", "a", "b", "b", "b", "a",
  "a", "b", "a", "b", "b", "b", "a", "a", "b", "a", "b", "b", "b"
), sex = c(
  "M", "F", "M", "M", "M", "F", "F", "F", "M", "M",
  "M", "F", "F", "F", "M", "M", "M", "F", "F", "F", "F", "M", "M",
  "F", "F", "F", "F", "M", "M", "F", "F", "F", "F", "M", "F", "F",
  "F", "F", "F", "M", "F", "M", "F", "F", "F", "M", "F", "M", "M"
), distance = c(
  "a", "a", "a", "a", "b", "b", "b", "a", "a",
  "a", "a", "b", "b", "b", "a", "a", "a", "a", "b", "b", "b", "a",
  "a", "a", "a", "b", "b", "b", "a", "a", "a", "a", "b", "b", "b",
  "a", "a", "a", "a", "b", "b", "b", "a", "a", "a", "a", "b", "b",
  "b"
), edu = c(
  "x", "x", "x", "y", "y", "y", "z", "x", "x", "x",
  "y", "y", "y", "z", "x", "x", "x", "y", "y", "y", "z", "x", "x",
  "x", "y", "y", "y", "z", "x", "x", "x", "y", "y", "y", "z", "x",
  "x", "x", "y", "y", "y", "z", "x", "x", "x", "y", "y", "y", "z"
), lungfunction = c(
  45L, 23L, 25L, 45L, 70L, 69L, 90L, 23L, 25L,
  45L, 70L, 69L, 90L, 50L, 25L, 45L, 70L, 69L, 90L, 50L, 62L, 45L,
  70L, 69L, 90L, 50L, 62L, 45L, 70L, 69L, 90L, 50L, 62L, 45L, 23L,
  69L, 90L, 50L, 62L, 45L, 23L, 25L, 90L, 50L, 62L, 45L, 23L, 25L,
  45L
), no2 = c(
  40L, 70L, 50L, 60L, 30L, 25L, 80L, 70L, 50L, 60L,
  30L, 25L, 80L, 89L, 50L, 60L, 30L, 25L, 80L, 89L, 10L, 60L, 30L,
  25L, 80L, 89L, 10L, 40L, 30L, 25L, 80L, 89L, 10L, 40L, 70L, 25L,
  80L, 89L, 10L, 40L, 70L, 50L, 80L, 89L, 10L, 40L, 70L, 50L, 60L
), pm25 = c(
  15L, 20L, 36L, 48L, 25L, 36L, 28L, 20L, 36L, 48L,
  25L, 36L, 28L, 15L, 36L, 48L, 25L, 36L, 28L, 15L, 25L, 48L, 25L,
  36L, 28L, 15L, 25L, 15L, 25L, 36L, 28L, 15L, 25L, 15L, 20L, 36L,
  28L, 15L, 25L, 15L, 20L, 36L, 28L, 15L, 25L, 15L, 20L, 36L, 48L
)), row.names = c(NA, -49L), class = "data.frame")

data %>%
  mutate(age = age %>% recode("a" = "Adults", "b" = "Children")) %>%
  pivot_longer(c(no2, pm25)) %>%
  ggplot(aes(name, lungfunction, fill = distance)) +
  geom_violinhalf(data = ~ .x %>% filter(distance == "a"), flip = TRUE) +
  geom_violinhalf(data = ~ .x %>% filter(distance == "b")) +
  facet_nested(~ age + sex)

^{Created on 2022-04-04 by the reprex package (v2.0.0)}