Course contentsShow
← Mathematics
Lesson 2993 of 3,12159. Statistics — Descriptive and InferentialFree lesson

Shape of Distributions: Symmetry and Skewness

Identify symmetric, left-skewed, and right-skewed distributions from graphs and measures.

Shape of Distributions: Symmetry and Skewness

What you'll learn: How to identify whether a distribution is symmetric, left-skewed, or right-skewed by examining its shape and summary statistics.

The Core Idea

When you visualize data with a histogram or density curve, the shape tells you how values are spread around the center. Three fundamental shapes appear repeatedly:

  • Symmetric: The left and right sides mirror each other around the center. Think of a perfectly balanced see-saw.
  • Right-skewed (positively skewed): A long tail stretches to the right. Most data clusters on the left, but a few extreme high values pull the tail rightward.
  • Left-skewed (negatively skewed): A long tail stretches to the left. Most data clusters on the right, with a few extreme low values creating the left tail.

Reading Graphs

In a histogram or box plot, look for:

  • Symmetric: Both tails roughly equal length; median sits in the middle
  • Right-skewed: Right tail longer; median left of center; possible right-side outliers
  • Left-skewed: Left tail longer; median right of center; possible left-side outliers

Using Measures

The relationship between mean, median, and mode reveals skewness:

  • Symmetric: Mean ≈ Median ≈ Mode (all roughly equal)
  • Right-skewed: Mode < Median < Mean (mean pulled right by extreme highs)
  • Left-skewed: Mean < Median < Mode (mean pulled left by extreme lows)

Visual Analogy

Imagine skewness as a weighted rope. Symmetric is balanced in the middle. Right-skewed has heavy weights on the right end, stretching it out. Left-skewed has weights on the left, pulling that side longer.

Key Takeaway: Symmetric distributions mirror around their center with mean ≈ median; right-skewed distributions have long right tails with mean > median; left-skewed distributions have long left tails with mean < median.