In short
The correlation coefficient (r) measures the strength and direction of a linear relationship between two variables, from −1 (perfectly negative) through 0 (none) to +1 (perfectly positive).
Key takeaways
- Squaring it gives the coefficient of determination used in regression.
- Correlation doesn't prove that one variable causes the other.
- It can miss strong relationships that aren't linear.
Where it's tested
BAR: Data Analytics for Accounting — study notes, a five-minute revision sheet and practice questions.
Practise: 3 questions
Question 1 of 3 · 0 answered
The correlation coefficient between employee overtime hours and error rates is −0.9. What does this indicate?