DetectingDiseases

# Set seed for reproducibility
set.seed(123)

# Define the number of iterations
n_iterations <- 10000

# Define the categories and their percentages
categories <- c("dispos", "disneg", "nodisneg", "nodispos")
percentages <- c(71.25, 3.75, 24.5, 0.5)

# Convert percentages to probabilities
probabilities <- percentages / 100

# Initialize a data frame to store the results
results <- data.frame(
  Iteration = integer(n_iterations),
  Category = character(n_iterations),
  stringsAsFactors = FALSE
)

# Assign points to categories based on the specified probabilities
for (i in 1:n_iterations) {
  results$Iteration[i] <- i
  results$Category[i] <- sample(categories, size = 1, prob = probabilities)
}

# View the first few rows of the results
head(results)

##   Iteration Category
## 1         1   dispos
## 2         2 nodisneg
## 3         3   dispos
## 4         4 nodisneg
## 5         5 nodisneg
## 6         6   dispos

# Optionally, you can summarize the counts of each category
summary_table <- table(results$Category)
print(summary_table)

## 
##   disneg   dispos nodisneg nodispos 
##      343     7167     2444       46