連續變項的處理方式

請先確認 Excel 檔與 R 程式位於同一個資料夾，並依自己的檔名與欄位名稱調整語法。

01載入套件與資料

library(readxl)
library(dplyr)
library(janitor)
library(ggplot2)

data <- read_excel("demo_polisci_中文.xlsx")

02查看原始年齡分布

data |>
  ggplot(aes(x = 年齡)) +
  geom_histogram(
    binwidth = 5,
    boundary = 0,
    fill = "#3976A8",
    color = "white"
  ) +
  labs(
    title = "受訪者年齡分布",
    x = "年齡",
    y = "人數"
  ) +
  theme_minimal(base_family = "Microsoft JhengHei")

03依指定切點建立年齡組

data <- data |>
  mutate(
    年齡組 = cut(
      年齡,
      breaks = c(18, 30, 40, 50, 60, Inf),
      labels = c(
        "18–29歲",
        "30–39歲",
        "40–49歲",
        "50–59歲",
        "60歲以上"
      ),
      right = FALSE,
      include.lowest = TRUE,
      ordered_result = TRUE
    )
  )

04製作年齡組次數分配表

tab_age_group <- data |>
  tabyl(年齡組) |>
  adorn_totals("row") |>
  adorn_pct_formatting(digits = 1)

tab_age_group

05繪製年齡組長條圖

age_plot <- data |>
  filter(!is.na(年齡組)) |>
  ggplot(aes(x = 年齡組)) +
  geom_bar(
    fill = "#3976A8",
    color = "white"
  ) +
  labs(
    title = "受訪者年齡分布",
    x = "年齡組",
    y = "人數"
  ) +
  theme_minimal(base_family = "Microsoft JhengHei")

age_plot

選用快速建立每 10 歲一組

data <- data |>
  mutate(
    年齡組 = cut(
      年齡,
      breaks = c(seq(0, 100, by = 10), Inf),
      labels = c(
        paste0(
          seq(0, 90, by = 10),
          "–",
          seq(9, 99, by = 10),
          "歲"
        ),
        "100歲以上"
      ),
      right = FALSE,
      include.lowest = TRUE,
      ordered_result = TRUE
    )
  )

選用儲存圖檔

ggsave(
  filename = "年齡組次數分配圖.png",
  plot = age_plot,
  width = 10,
  height = 6,
  dpi = 300,
  bg = "white"
)