PMCC and Correlation (AA HL)
Pearson's product-moment correlation coefficient measures the strength and direction of a linear relationship, with . Find using technology, then describe it: the sign gives the direction and the size of gives the strength. It also covers why correlation does not prove causation. It's part of the broader Bivariate Statistics topic.
14 questions on this sub-topic.
Syllabus
| Code | Syllabus content |
|---|---|
| SL4.4 | Linear correlation of bivariate data; Pearson's product-moment correlation coefficient , found using technology. Scatter diagrams; lines of best fit by eye, through the mean point. Distinction between correlation and causation. Equation of the regression line of on , and use for prediction, including the dangers of extrapolation. Interpreting the parameters and in . |
Official IB source: Mathematics: analysis and approaches subject brief (PDF, ibo.org).
Skills practised on this page:
- Calculate the Pearson's product-moment correlation coefficient using technology, and interpret its strength and direction.
- Distinguish correlation from causation, recognizing that correlation does not imply causation.
Interpreting r
Pearson's correlation coefficient
On the formula booklet, but always found using technology in practice: close to means a strong linear correlation, close to means little or none.
Correlation vs causation
A strong never proves one variable causes the other - a third factor could be driving both, or the link could be coincidental.
Need the full syllabus wording and the wider statistics formula table? See Bivariate Statistics. For calculator steps, see the parent topic's GDC guidance.
Key terms
What does the sign of tell you?
A positive means tends to increase as increases. A negative means tends to decrease as increases.
e.g. shows that as increases, tends to decrease.
What does the size of tell you?
The closer is to , the stronger the linear relationship, and the closer to , the weaker it is. The sign does not affect the strength.
e.g. shows a stronger linear relationship than , because .
What is a confounding variable?
A confounding variable is a third variable that influences both of the quantities being compared. It can produce a correlation between them even though neither causes the other.
e.g. Daily temperature can raise both the number of people swimming and the number of sunburn cases, so these two correlate without either causing the other.
Why should you look at the scatter diagram as well as ?
only measures how well the points fit a straight line. A scatter diagram shows curved patterns and outliers that alone can hide.
e.g. The points for lie exactly on a curve, yet .
Worked examples
Two quantities have Pearson’s product-moment correlation coefficient .
(a) Describe the linear relationship.
(b) State what would indicate.
Worked solution
(a) Strong A1
negative linear correlation. A1
(b) No linear correlation between the variables. A1
A study finds a strong positive correlation between ice-cream sales and drowning incidents.
(a) Suggest a confounding variable.
(b) Explain how it produces the correlation without direct causation.
Worked solution
(a) Hot weather (temperature). A1
(b) Higher temperatures increase both ice-cream sales and swimming (hence drownings), R1
This produces a correlation between the variables without either one causing the other. A1
A scatter plot shows a strong positive trend except for one point far below.
Describe the effect of this outlier on
Worked solution
The outlier lies far off the otherwise tight trend, weakening the linear fit. R1
This reduces the magnitude of (closer to 0). R1
Common mistakes
- Treating correlation as causation. A strong shows two variables move together, not that one causes the other - a third factor, or coincidence, could explain the pattern.
- Confusing the sign of with its strength. is a stronger correlation than , even though it's negative - strength is about how close is to , not about the sign.
- Ignoring outliers when judging . A single far-off point can pull noticeably towards even when the rest of the data shows a tight linear trend, so a low doesn't always mean "no relationship".
Using your GDC
Every step below is a real button sequence, not a vague "use your calculator" hint - covering the TI-84 Plus, TI-Nspire, and Casio fx-9860/fx-CG50. Pick your model to filter down to just the steps that apply to you.
Gives the regression line and the correlation coefficient in one step - the core skill for this whole topic.
- Enter x-values in one list and y-values in another.
- Turn on DiagnosticOn once (2nd → CATALOG) so appears; then STAT → CALC → 4:LinReg(ax+b), set Xlist and Ylist, Calculate.TI-84
- Calculator page → menu → Statistics → Stat Calculations → Linear Regression (mx+b).Nspire
- Statistics menu → CALC (F2) → REG (F3) → X (linear); shows automatically.Casio
- Read (gradient), (intercept), (correlation) and (coefficient of determination).
- Use the equation to predict - but only within the data range (interpolation).
Tip: near means a strong linear fit; near means weak. is the proportion of variation explained.
Lists let you store paired data sets without re-entering values - essential for setting up and columns before running a regression.
- Enter data manually: go to the list editor and type -values and -values into two separate lists.
- 2nd → STAT (LIST) → OPS lets you sort or clear a list. Use L1 for , L2 for , and reference both together in LinReg.TI-84
- In a Lists & Spreadsheet page, use two named columns for and so both are available together for regression.Nspire
- In Statistics list editor, enter -values in List 1 and -values in List 2 before running REG.Casio
- Keep the and lists the same length and in matching pairs - a mismatched row shifts every pair after it.
Tip: Double-check the lists are paired correctly before running a regression - a single mistyped value can shift noticeably.
See the full GDC guide for more calculator models and topics.
Quick questions
What does Pearson's correlation coefficient r measure?
measures the strength and direction of the linear relationship between two variables, ranging from (perfect negative) to (perfect positive), with meaning no linear correlation.
Does a strong correlation mean one variable causes the other?
No. A strong only shows the two variables move together - it never proves causation, since a third (confounding) factor could be driving both, or the pattern could be coincidental.
What does r = 1 or r = -1 mean?
Every point lies exactly on a straight line. The line has a positive gradient when and a negative gradient when .
Can r be greater than 1?
No, always lies between and inclusive. A value outside this range means there has been a mistake in the calculation.
Do outliers affect the value of r?
Yes, a single outlier can raise or lower noticeably. Check the scatter diagram and comment on any outlier before interpreting .
Ready to practise properly?
14 correlation questions, marked instantly like the real exam.