Standard Deviation (Conceptual)

TipLearning Objectives

By the end of this lesson, you’ll be able to:

  • Understand standard deviation as a measure of spread.
  • Compare datasets using standard deviation.
  • Predict how changes (adding constants, scaling) affect standard deviation.
  • Recognize how outliers affect spread.

Key Ideas

Standard deviation measures how spread out the data are from the mean.

Conceptually:

  • Low SD → values clustered tightly around the mean
  • High SD → values spread out widely
  • SD ≥ 0 always
  • Outliers increase SD

You don’t need the full formula for SAT-level questions; focus on conceptual comparisons.

How Changes Affect Standard Deviation

  • Adding/subtracting a constant → no change in SD
  • Multiplying all numbers by a constant \(k\) → SD multiplied by \(|k|\)
  • Adding an outlier → SD increases
  • Making values more consistent → SD decreases

Common Problem Types

Comparing Spread From Lists

Look for which dataset is more “spread out.”

Example:
A: 50, 51, 49 (tight cluster)
B: 20, 80, 10 (very spread out)
→ B has larger SD.

Determining Standard Deviation After Shifts

Adding or subtracting a constant does not change SD.

Example:
[3, 7, 9] → add 10 → [13, 17, 19]
Spread unchanged → SD unchanged.

Determining Standard Deviation After Scaling

Multiplying all values by \(k\) multiplies SD by \(|k|\).

Example:
Multiply by −2 → SD doubles.

Effect of Outliers

Large deviations from the mean increase SD.

Example:
[5, 6, 7] vs [5, 6, 7, 100]
SD increases with the outlier.

Comparing Spread Using Graphs (Boxplots/Histograms)

Wider boxplots or histograms indicate larger SD.

Example:
A wider box in a boxplot → larger IQR → typically larger SD.

Strategies

  • Look at how far values deviate from the mean, not the mean itself.
  • Use visual clues: wide vs narrow distributions.
  • Remember that shifting all values does not affect SD.
  • Check effect of scaling and outliers.

Worked Examples

Example 1 — Which set has larger SD?

Set A: 50, 51, 49, 50
Set B: 20, 80, 10, 150

Set B is more spread out → much larger SD.

Example 2 — Add 10 to all values

Data: \([4,8,12]\) → \([14,18,22]\)
Spread is unchanged → SD stays the same.

Example 3 — Multiply by 3

Data: \([5,6,7]\) → \([15,18,21]\)
SD is multiplied by 3.

Example 4 — Introduce an outlier

\([10,11,12]\) → \([10,11,12,100]\)
Spread increases dramatically → SD increases.

WarningCommon Mistakes
  • Thinking the mean affects SD (it doesn’t; spread matters).
  • Believing SD decreases when a constant is added/subtracted.
  • Forgetting that outliers strongly increase SD.
  • Assuming equal ranges means equal SD (shape matters too).

Practice Problems

  1. Which has larger SD: \([9,10,11]\) or \([3,20,37]\)?
  2. If every value increases by 7, what happens to SD?
  3. Multiply all values by \(-2\). What happens to SD?
  4. Adding one outlier to a dataset — SD goes up, down, or stays same?
  1. \([3,20,37]\) has a greater spread → larger SD.
  2. SD stays the same.
  3. SD multiplied by \(|{-2}| = 2\).
  4. Outlier → SD increases.

Summary

  • SD measures spread around the mean.
  • Shifting does nothing; scaling multiplies SD.
  • Outliers increase SD significantly.
  • To compare SD quickly: look at which dataset is “wider.”
  • SD doesn’t care about the mean — only spread.
  • If values become more consistent, SD decreases.