002_linear_regression

linear_regression.R

# Calculate coefficients
b1 <- (sum((x - mean(x)) * (y - mean(y)))) / (sum((x - mean(x))^2))
b0 <- mean(y) - b1 * mean(x)

# Define function for generating predictions
simple_lr_predict <- function(x) {
  return(b0 + b1 * x)
}

# Apply simple_lr_predict() to input data
simple_lr_predictions <- sapply(x, simple_lr_predict)
simple_lr_data$yhat <- simple_lr_predictions

# Visualize input data and the best fit line
ggplot(data = simple_lr_data, aes(x = x, y = y)) +
  geom_point(size = 3, color = "#0099f9") +
  geom_line(aes(x = x, y = yhat), size = 2) +
  theme_classic() +
  labs(
    title = "Applying simple linear regression to data",
    subtitle = "Black line = best fit line"
  )