Skip to main content

📏 Mean, Median, and Mode

These are our basic tools for finding the "center" of our data.

🧮 Mean vs Median

  • Mean: Add everything up, divide by the count. Highly sensitive to outliers.
  • Median: Line everyone up by height, pick the person exactly in the middle. Ignores extreme outliers.

🐍 Python Implementation

Let's see how an outlier (Bill Gates walking into a bar) affects the Mean but not the Median!

import numpy as np
from scipy import stats

# Normal incomes in a bar
incomes = [50000, 60000, 55000, 45000, 70000]

print("Normal Mean:", np.mean(incomes))
print("Normal Median:", np.median(incomes))

# Bill Gates walks in!
incomes.append(1_000_000_000)

print("\nMean with Bill Gates:", np.mean(incomes)) # Huge jump!
print("Median with Bill Gates:", np.median(incomes)) # Barely changes!