Resources For Teachers For Tutors For Students & Parents Pricing
Algebra Data and statistics

Correlation coefficient

20 practice questions 2 video lessons Theory + worked examples
Practice 20 questions
Practice questions

Every question with a fully worked solution.

Start practising
Watch 2 video(s)
  • Calculating correlation coefficient r | AP Statistics | Khan Academy Watch
  • Correlation Coefficient Watch
Create a free accountTrack your progress and save your work as you go.
Create free account

Theory

The correlation coefficient \(r\) measures a linear relationship:

\[-1\le r\le 1.\]
  • The sign gives the direction (positive or negative).
  • \(|r|\) near \(1\) is a strong fit; near \(0\) is weak.
\(r=\pm1\) means the points lie exactly on a line.
The correlation coefficient r The correlation coefficient r ranges from -1 to 1, measuring the direction and strength of a linear relationship. -1 0 1 strong neg none strong pos
\(r\) runs from \(-1\) to \(1\).
Correlation coefficient r Correlation coefficient r Correlation coefficient r -1 ≀ r ≀ 1 sign: direction (+ or -) |r| near 1: strong; near 0: weak
Interpreting \(r\).

The range:

\[-1\le r\le 1\]
r ranges from negative 1 to 1
Sign is direction; magnitude is strength.

How to interpret r

  1. Read the sign for the direction.
  2. Read \(|r|\) for the strength.
  3. Near \(1\): strong; near \(0\): weak.
  4. Use technology to compute \(r\).
Example 1 β€” Strong positive
Describe a correlation with \(r=0.95\).
Solution

\(|r|\) near \(1\) and positive.

\(r=0.95\)\(\Rightarrow\)\(\text{strong positive}\)
a strong positive correlation
Example 2 β€” Weak
Describe \(r=0.1\).
Solution

\(|r|\) near \(0\) is weak.

\(r=0.1\)\(\Rightarrow\)\(\text{weak}\)
a weak correlation
Example 3 β€” Negative
Describe \(r=-0.8\).
Solution

Negative and fairly strong.

\(r=-0.8\)\(\Rightarrow\)\(\text{strong negative}\)
a strong negative correlation
Example 4 β€” Range of r
What values can \(r\) take?
Solution

From \(-1\) to \(1\).

\(-1\)\(\le\)\(r\le1\)
negative 1 to 1

Common pitfalls

\(|r|\) near 1 is strong, near 0 is weak.
\(r\) measures linear fit only.
A strong \(r\) is not causation.

Frequently asked questions

What does the correlation coefficient measure?

The direction and strength of a linear relationship.

What is the range of r?

\(-1\) to \(1\).

What does \(r=0.95\) mean?

A strong positive correlation.

What does \(r=0\) mean?

No linear correlation.