Course contentsShow
← Data Science
Lesson 53 of 2,1452. Descriptive Statistics FoundationsFree lesson

Coefficient of Variation

Use CV to compare variability across datasets with different units or scales.

Coefficient of Variation

What you'll learn: How to fairly compare the variability of datasets that have different units or scales using a standardized measure.

The Problem with Direct Comparisons

Imagine you want to compare the consistency of two products: one is measured in grams (weights ranging 5–15g with SD = 2g) and another in kilometers (distances ranging 100–300km with SD = 50km). Which varies more? You can't simply compare 2 vs 50 — the units are completely different!

What is the Coefficient of Variation?

The Coefficient of Variation (CV) solves this by expressing variability as a percentage of the mean. It's calculated as:

CV = (Standard Deviation / Mean) × 100%

By dividing the standard deviation by the mean, you create a unitless ratio that shows how large the spread is relative to the average value.

Why It Matters

The CV lets you answer: "Proportionally speaking, which dataset is more variable?"

Example:

  • Product A (grams): Mean = 10g, SD = 2g → CV = (2/10) × 100% = 20%
  • Product B (kilometers): Mean = 200km, SD = 50km → CV = (50/200) × 100% = 25%

Despite the larger absolute standard deviation, Product B is actually more variable relative to its scale.

When to Use CV

  • Comparing datasets with different units (salary in USD vs height in cm)
  • Comparing datasets with very different means (bacteria counts vs human populations)
  • Assessing relative risk or consistency in finance, manufacturing, or quality control

Key Takeaway: The Coefficient of Variation standardizes variability as a percentage, enabling fair comparisons across datasets with different units or scales.