Correlation

Statistics
definition

Also known as: r, correlation coefficient

Grade 6-8

View on concept map

Correlation measures the strength and direction of the linear relationship between two quantitative variables, ranging from -1 to +1. Correlation is the first tool for exploring relationships between variables — but it only captures linear association, not causation or nonlinear patterns.

Definition

Correlation measures the strength and direction of the linear relationship between two quantitative variables, ranging from -1 to +1.

💡 Intuition

Do two things go up and down together? r = +1 means perfectly together, r = -1 means perfectly opposite.

🎯 Core Idea

Correlation r near \pm 1 means a strong linear relationship; r near 0 means little linear association. Sign indicates direction (positive or negative slope).

Example

Height and weight: r \approx 0.7 (positive). Temperature and heating bill: r < 0 (negative).

Formula

r \text{ ranges from } -1 \text{ to } +1

Notation

r is the sample correlation coefficient; \rho (rho) is the population correlation

🌟 Why It Matters

Correlation is the first tool for exploring relationships between variables — but it only captures linear association, not causation or nonlinear patterns.

💭 Hint When Stuck

Draw a scatter plot first. If points trend upward, r is positive; downward, r is negative; no trend, r is near zero.

Formal View

r = \frac{1}{n-1}\sum_{i=1}^{n}\left(\frac{x_i - \bar{x}}{s_x}\right)\left(\frac{y_i - \bar{y}}{s_y}\right) where -1 \leq r \leq 1

🚧 Common Stuck Point

Correlation does not imply causation. Ice cream sales and drownings both correlate with summer.

⚠️ Common Mistakes

  • Concluding that correlation implies causation — two variables can correlate because of a lurking third variable
  • Assuming r = 0 means no relationship at all — it means no LINEAR relationship; a strong curved relationship can have r \approx 0
  • Interpreting r = 0.5 as 'halfway to perfect correlation' — r^2 = 0.25, so only 25\% of variation is explained

Frequently Asked Questions

What is Correlation in Math?

Correlation measures the strength and direction of the linear relationship between two quantitative variables, ranging from -1 to +1.

Why is Correlation important?

Correlation is the first tool for exploring relationships between variables — but it only captures linear association, not causation or nonlinear patterns.

What do students usually get wrong about Correlation?

Correlation does not imply causation. Ice cream sales and drownings both correlate with summer.

What should I learn before Correlation?

Before studying Correlation, you should understand: mean, standard deviation.

How Correlation Connects to Other Ideas

To understand correlation, you should first be comfortable with mean and standard deviation. Once you have a solid grasp of correlation, you can move on to regression inference and scatter plot.

← Back to Explorer

Visualization

Static

Visual representation of Correlation