australia.R

# Load required libraries
library(dplyr)
library(ggplot2)

# Set seed for reproducibility
set.seed(123)

# Define hospitals
hospitals <- c("Hospital A", "Hospital B", "Hospital C", "Hospital D", "Hospital E")

# Generate synthetic data
data <- expand.grid(
  Hospital = hospitals,
  Year = 2001:2020
) %>%
  mutate(
    Cancer_Deaths = round(rnorm(n(), mean = 30, sd = 5)),  # Simulate number of cancer deaths
    Cancer_Type = sample(c("Lung", "Breast", "Colorectal", "Prostate", "Pancreatic"), n(), replace = TRUE),  # Simulate cancer type
    Age_Group = sample(c("Under 40", "40-60", "Over 60"), n(), replace = TRUE, prob = c(0.2, 0.5, 0.3)),  # Simulate patient age group
    Gender = sample(c("Male", "Female"), n(), replace = TRUE),  # Simulate patient gender
    Socioeconomic_Status = sample(c("Low", "Medium", "High"), n(), replace = TRUE, prob = c(0.3, 0.4, 0.3))  # Simulate patient socioeconomic status
  )

# Plot the graph
ggplot(data, aes(x = Year, y = Cancer_Deaths, color = Hospital)) +
  geom_line() +
  labs(title = "Number of Cancer Deaths by Hospital (2001-2020)",
       x = "Year",
       y = "Number of Cancer Deaths",
       color = "Hospital")


# Count of Unique Hospitals
cat("Test 1: Count of unique hospitals:", length(unique(data$Hospital)), "\n")

# Check for Missing Values in Cancer Deaths
cat("Test 2: Any missing values in cancer deaths column:", anyNA(data$Cancer_Deaths), "\n")

# Check Unique Cancer Types
cat("Test 3: Unique cancer types:", unique(data$Cancer_Type), "\n")

# Count of Unique Age Groups
cat("Test 4: Count of unique age groups:", length(unique(data$Age_Group)), "\n")

# Proportion of Males and Females
cat("Test 5: Proportion of males and females:\n", table(data$Gender) / nrow(data), "\n")

# Check for Missing Values in Socioeconomic Status
cat("Test 6: Any missing values in socioeconomic status column:", anyNA(data$Socioeconomic_Status), "\n")

# Average Number of Cancer Deaths per Hospital
cat("Test 7: Average number of cancer deaths per hospital:\n", tapply(data$Cancer_Deaths, data$Hospital, mean), "\n")

# Check Distribution of Cancer Deaths by Cancer Type
cat("Test 8: Distribution of cancer deaths by cancer type:\n", table(data$Cancer_Type), "\n")

# Check Distribution of Cancer Deaths by Age Group
cat("Test 9: Distribution of cancer deaths by age group:\n", table(data$Age_Group), "\n")

# Check Distribution of Cancer Deaths by Socioeconomic Status
cat("Test 10: Distribution of cancer deaths by socioeconomic status:\n", table(data$Socioeconomic_Status), "\n")


library(rstanarm)

# Build Bayesian regression model
model <- stan_glm(Cancer_Deaths ~ Cancer_Type + Age_Group + Gender + Socioeconomic_Status,
                  data = data,
                  family = poisson(link = "log"),
                  prior = normal(0, 2.5),
                  prior_intercept = normal(0, 2.5))

# Summary of the model
summary(model)

generated by ChatGPT^