Variance: Average Squared Deviations
You'll learn what variance is and why we square deviations to measure spread.
The Core Idea
Variance builds on what you already know about the mean. It measures how spread out your data is by calculating the average of the squared differences between each data point and the mean.
Here's the process:
- Find the mean of your dataset
- Subtract the mean from each data point (these are "deviations")
- Square each deviation (to make them all positive and emphasize larger differences)
- Average those squared deviations
Why Square the Deviations?
If we just averaged the raw deviations, positive and negative differences would cancel out, giving us zero—not helpful! Squaring ensures all values are positive and also gives more weight to extreme values, making variance sensitive to outliers.
Understanding the Units
Here's something important: variance has squared units. If your data measures height in centimeters, variance will be in centimeters squared. If you're measuring test scores (unitless), variance is in squared points. This makes variance less intuitive than the original data, which is why we often use its square root (standard deviation) for interpretation—but you haven't learned that yet!
A Simple Analogy
Think of variance like measuring how "wild" a group of friends' opinions are. If everyone agrees closely (low variance), their views cluster near the average. If opinions are all over the place (high variance), the squared deviations capture that chaos numerically.
Key Takeaway: Variance quantifies data spread as the mean of squared deviations from the mean, resulting in values expressed in squared units of the original measurement.