A skew (or skewness) is a way of describing how lopsided a distribution of values is, instead of being perfectly balanced like a bell curve.

What “skew” means in simple terms

Think of a graph of your data:

  • If the left and right sides are mirror images, skew is about zero (pretty symmetrical).
  • If one side has a long thin “tail” of rare extreme values, the distribution is skewed toward that side.

In everyday terms: skew tells you which side has more extreme outliers and how strongly the data lean in that direction.

Types of skew

  • Right (positive) skew :
    • Long tail to the right (high values).
* A few very large values pull the mean to the right.

* Common example: incomes in a population, where a small number of very high earners stretch the right tail.
  • Left (negative) skew :
    • Long tail to the left (low values).
* A few very low values pull the mean to the left.

* Example: exam scores when most people do very well but a few score very low.
  • Zero (or near‑zero) skew :
    • Shape is roughly symmetric, mean and median are close.

Quick visual example

  • Imagine test scores from 0–100:
    • Most students score 70–90, but a few score 10–20 → long left tail → left/negative skew.
* Most students score 30–50, but some score 95–100 → long right tail → right/positive skew.

Why skew matters (the “so what”)

  • It affects which statistics are sensible:
    • In skewed data, the median can describe “typical” better than the mean.
  • It affects which models and tests are appropriate, because many standard methods assume symmetry or normality.
  • It helps you spot outliers and risk , for example in finance where skewness is used to understand the likelihood of big gains or big losses.

Mini SEO-style notes

  • Focus phrase “what is a skew”: It refers to the asymmetry of a data distribution, usually described as right (positive) or left (negative) skew.
  • In recent trading and risk discussions, skewness is a trending topic because it highlights non‑normal risk profiles in markets.

TL;DR: Skew (skewness) is a measure of how asymmetric a distribution is and which side has the long tail of extreme values, often summarized as positive (right) or negative (left).

Information gathered from public forums or data available on the internet and portrayed here.