Homework 4

homework
code
analysis
Author

Brett Patmore

Published

May 10, 2024

Let’s analyze the homework 4 data:

health_cust <- read_csv('https://bcdanl.github.io/data/custdata_rev.csv')

Housing Type Statistics

housing_type_statistics <- health_cust |> 
  group_by(housing_type) |> 
  summarize(
    mean = mean(income, na.rm = TRUE),
    SD = sd(income, na.rm = TRUE),
    Q1 = quantile(income, probs = 0.25, na.rm = TRUE),
    Median = median(income, na.rm = TRUE),
    Q3 = quantile(income, probs = 0.75, na.rm = TRUE), 
    Max = max(income, na.rm = TRUE)
  )

State of Residency Statistics

state_statistics <- health_cust |> 
  group_by(state_of_res) |> 
  summarize(
    mean = mean(income, na.rm = TRUE),
    SD = sd(income, na.rm = TRUE),
    Q1 = quantile(income, probs = 0.25, na.rm = TRUE),
    Median = median(income, na.rm = TRUE),
    Q3 = quantile(income, probs = 0.75, na.rm = TRUE), 
    Max = max(income, na.rm = TRUE)
  )

Marital Status Statistics

marital_statistics <- health_cust |> 
  group_by(marital_status) |> 
  summarize(
    mean = mean(income, na.rm = TRUE),
    SD = sd(income, na.rm = TRUE),
    Q1 = quantile(income, probs = 0.25, na.rm = TRUE),
    Median = median(income, na.rm = TRUE),
    Q3 = quantile(income, probs = 0.75, na.rm = TRUE), 
    Max = max(income, na.rm = TRUE)
  )

Income by Housing Type

income_by_housing_type <- health_cust |> 
  group_by(income, housing_type) |> 
  summarize(Count = n(), .groups = "drop") |> 
  group_by(housing_type) |> 
  arrange(desc(income))