Scribe logoScribeNotes & practice
Sign inStart free
  1. Notes
  2. ›IB Mathematics: Applications and Interpretation
  3. ›4 Statistics and probability
  4. ›4.4 Correlation and regression

IB Mathematics: Applications and Interpretation · Topic 4 · Statistics and probability

4.4 Correlation and regression

Plot a scatter diagram, describe the strength and direction of correlation, and use a regression line to interpret and predict values.

  • 5 min read
  • 5 parts
  • 10 questions
  • Draft
Start a Quick 5 on this topic→Jump to the 10 questions
1/5A scatter diagram shows how two variables are related
  1. 1A scatter diagram shows how two variables are related
  2. 2Correlation describes the direction and strength of a pattern
  3. 3Pearson’s r gives a number for the strength of linear correlation
  4. 4A regression line models the trend between two variables
  5. 5Predictions are reliable only inside the range of the data
  6. Check your recall
  7. Practice: 10 questions
1

Part 1 of 5: A scatter diagram shows how two variables are related

Suppose you record the hours a student revises and the score in a test. Each student gives a pair of values. Data in pairs like this is bivariate data.

To display it, draw a scatter diagram. Put the independent variable, the one you choose or control, on the horizontal axis. Put the dependent variable, the one that responds, on the vertical axis. Plot one point for each pair.

Always plot the data before calculating anything. The diagram shows whether a straight line is a sensible model.

Exam tip

Label each axis with its variable and units. Choose scales that spread the points across the grid.

Key terms · tap one for its definition

bivariate data

Bivariate data is a set of paired values, with two variables recorded for each individual or item.

scatter diagram

A scatter diagram is a graph that plots each pair of values as one point, with one variable on each axis.

Part 1 done

2

Part 2 of 5: Correlation describes the direction and strength of a pattern

Now look at the overall pattern of the points. With positive correlation, the points slope upwards from left to right. With negative correlation, they slope downwards.

Strength depends on how closely the points follow a straight line. Tight clusters show strong correlation, and loose scatter shows weak correlation. If there is no pattern, there is no correlation. Correlation here always means a straight-line pattern.

Sometimes one point lies far from the rest. This is an outlier. Check whether it is an error before deciding to keep it.

Key terms · tap one for its definition

positive correlation

Positive correlation is a tendency for yyy to increase as xxx increases, giving r>0r>0r>0.

negative correlation

Negative correlation is a tendency for yyy to decrease as xxx increases, giving r<0r<0r<0.

outlier

An outlier is a data point that lies unusually far from the pattern formed by the other points.

Part 2 done

Quick check

One question on the part you just read

Easy

Identify the description that matches a correlation coefficient of r=−0.92r=-0.92r=−0.92.
Show answer and explanation

Answer: A · Worked explanation

A value of -0.92 is close to -1, so the linear correlation is strong. The negative sign shows that yyy tends to decrease as xxx increases. A weak description would suit a value near 0, and a positive description would need a positive sign, which is the tempting error.
3

Part 3 of 5: Pearson’s r gives a number for the strength of linear correlation

Words such as ‘strong’ are vague, so we also use a number. Pearson’s product-moment correlation coefficient, rrr, measures linear correlation. Your calculator finds it from the data. A perfect correlation puts every point exactly on a straight line.

The value of rrr always lies between -1 and +1+1+1. The sign gives the direction. The size, ignoring the sign, gives the strength, and values near either end show strong correlation.

A rough guide to interpreting r

Value of rrrDescription
r=+1r=+1r=+1Perfect positive linear correlation
rrr near +0.9+0.9+0.9Strong positive correlation
rrr near +0.5+0.5+0.5Moderate positive correlation
rrr near 0Little or no linear correlation
rrr near -0.9Strong negative correlation
r=−1r=-1r=−1Perfect negative linear correlation
Value of $r$
r=+1r=+1r=+1
Description
Perfect positive linear correlation
Value of $r$
rrr near +0.9+0.9+0.9
Description
Strong positive correlation
Value of $r$
rrr near +0.5+0.5+0.5
Description
Moderate positive correlation
Value of $r$
rrr near 0
Description
Little or no linear correlation
Value of $r$
rrr near -0.9
Description
Strong negative correlation
Value of $r$
r=−1r=-1r=−1
Description
Perfect negative linear correlation

Common mistake

A value of rrr near 0 does not mean the variables are unrelated. A curved pattern can give rrr near 0.

Key term

Pearson’s product-moment correlation coefficient

Pearson’s product-moment correlation coefficient, rrr, is a number from -1 to +1+1+1 measuring the strength and direction of linear correlation.

Part 3 done

4

Part 4 of 5: A regression line models the trend between two variables

When points lie near a straight line, a line of best fit can model the trend. The regression line of yyy on xxx is the least squares line. It makes the sum of the squared vertical distances from the points as small as possible. Your calculator gives its equation as y=ax+by=ax+by=ax+b.

The line always passes through the mean point, (xˉ,yˉ)(\bar{x},\bar{y})(xˉ,yˉ​).

Figure 1. Eight students’ results rise steadily with revision time. The regression line y = 4.25x + 42.25 passes close to every point.

The gradient aaa is the average change in yyy for each increase of 1 in xxx. The intercept bbb is the predicted value of yyy when x=0x=0x=0. In the revision data, a=4.25a=4.25a=4.25, b=42.25b=42.25b=42.25 and r≈0.994r\approx0.994r≈0.994. Each extra hour of revision goes with about 4.25 extra marks.

Key terms · tap one for its definition

regression line

The regression line of yyy on xxx is the least squares line y=ax+by=ax+by=ax+b, used to predict yyy from a given xxx.

mean point

The mean point is the point (xˉ,yˉ)(\bar{x},\bar{y})(xˉ,yˉ​) whose coordinates are the means of the xxx values and yyy values.

Part 4 done

Quick check

One question on the part you just read

Easy

Identify the pair of variables most likely to show negative correlation.
Show answer and explanation

Answer: D · Worked explanation

As a car gets older, its resale value usually falls, so the pair moves in opposite directions. Hours of revision with test score, height with arm span and distance with calories used all tend to rise together. Height with arm span is the most tempting wrong answer, but it shows positive correlation.
5

Part 5 of 5: Predictions are reliable only inside the range of the data

Now use the line to make predictions. Substitute a value of xxx into the equation to find a predicted yyy. Predicting within the range of the data is interpolation. Predicting beyond that range is extrapolation.

Worked example

Predict and judge reliability

The revision data cover 1 to 8 hours, and the regression line is y=4.25x+42.25y=4.25x+42.25y=4.25x+42.25. The test is marked out of 100. Predict the score for (a) 6 hours and (b) 14 hours.
  1. 1
    (a) Substitute x=6x=6x=6: y=4.25×6+42.25y=4.25\times6+42.25y=4.25×6+42.25.
  2. 2
    Evaluate: y=25.5+42.25=67.75y=25.5+42.25=67.75y=25.5+42.25=67.75. Since 6 lies inside 1 to 8, this is interpolation.
  3. 3
    (b) Substitute x=14x=14x=14: y=4.25×14+42.25=101.75y=4.25\times14+42.25=101.75y=4.25×14+42.25=101.75.
  4. 4
    Since 14 lies outside 1 to 8, this is extrapolation. The result exceeds the maximum mark, so it cannot be right.

Answer: (a) About 67.8 marks, a reliable interpolation. (b) The value 101.75 marks is an unreliable extrapolation.

A prediction assumes that the same pattern continues. This is more believable inside the data range than outside it. Use the line only to predict yyy from xxx. The line was built to predict yyy, so it should not be rearranged to estimate xxx.

Common mistake

Strong correlation does not prove that one variable causes the other. A third factor may influence both.

Key terms · tap one for its definition

interpolation

Interpolation is predicting a value of yyy for an xxx value inside the range of the data.

extrapolation

Extrapolation is predicting a value of yyy for an xxx value outside the range of the data.

Note read

Check your recall[14 marks]

6 written questions. Answer each one in your head or on paper, then open the mark scheme.

  1. 1.Describe[2 marks]

    Describe the correlation between two variables when r=−0.85r=-0.85r=−0.85.

    Show mark schemeHide mark scheme

    Model answer

    There is strong negative linear correlation. The second variable tends to decrease as the first increases.

    • 1 mark for stating that the correlation is negative
    • 1 mark for stating that the correlation is strong
  2. 2.Distinguish[2 marks]

    Distinguish between interpolation and extrapolation.

    Show mark schemeHide mark scheme

    Model answer

    Interpolation predicts yyy for an xxx value inside the range of the data. Extrapolation predicts yyy for an xxx value outside that range, so it is less reliable.

    • 1 mark for stating that interpolation uses an x value inside the range of the data
    • 1 mark for stating that extrapolation uses an x value outside the range of the data
  3. 3.Calculate[3 marks]

    Calculate the predicted value of yyy when x=12x=12x=12, using the regression line y=2.4x+18y=2.4x+18y=2.4x+18 found from data with xxx between 5 and 20. State whether this is interpolation or extrapolation.

    Show mark schemeHide mark scheme

    Model answer

    y=2.4×12+18=28.8+18=46.8y=2.4\times12+18=28.8+18=46.8y=2.4×12+18=28.8+18=46.8. Since 12 lies between 5 and 20, this is interpolation.

    • 1 mark for substituting x=12x=12x=12 into the equation
    • 1 mark for obtaining y=46.8y=46.8y=46.8
    • 1 mark for stating that this is interpolation because 12 lies inside the data range
  4. 4.Explain[2 marks]

    Explain why a strong correlation between two variables does not prove that one causes the other.

    Show mark schemeHide mark scheme

    Model answer

    Correlation only shows that the variables change together. A third factor may influence both, so the link need not be causal.

    • 1 mark for stating that correlation shows only that the variables change together
    • 1 mark for stating that a third factor may influence both variables
  5. 5.Deduce[3 marks]

    Deduce what these results tell a café owner. The regression line of hot drinks sold yyy against daily temperature xxx in ∘C^{\circ}\mathrm{C}∘C is y=−6x+210y=-6x+210y=−6x+210, and r=−0.93r=-0.93r=−0.93.

    Show mark schemeHide mark scheme

    Model answer

    The value r=−0.93r=-0.93r=−0.93 shows strong negative correlation. Hot drink sales tend to fall as the temperature rises. The gradient -6 means about 6 fewer drinks for each 1 ∘C1\,^{\circ}\mathrm{C}1∘C rise.

    • 1 mark for stating that rrr shows strong negative correlation
    • 1 mark for stating that sales tend to fall as temperature rises
    • 1 mark for interpreting the gradient as about 6 fewer drinks per 1 ∘C1\,^{\circ}\mathrm{C}1∘C rise
  6. 6.Sketch[2 marks]

    Sketch a scatter diagram that shows strong positive correlation and contains one outlier.

    Show mark schemeHide mark scheme

    Model answer

    Draw labelled axes. Plot points that rise from left to right and lie close to a straight line, with one point clearly far from the pattern.

    • 1 mark for drawing labelled axes with points sloping upwards close to a line
    • 1 mark for including one point clearly away from the pattern

Practice this topic

10 quick-fire multiple-choice questions, easy to hard. Tap an answer to see if you're right and the worked explanation. (The written questions with mark schemes are under “Check your recall” above.)

0 right0 of 10 answered

Includes the 2 quick checks in the note above.

3.

Easy·Identify[1 mark]

A teacher draws a scatter diagram to see whether revision time affects test score. Identify the correct way to plot it.
Show answer and explanation

Answer: C · Worked explanation

Revision time is the independent variable, so it goes on the horizontal axis. The test score responds, so it goes on the vertical axis. A scatter diagram plots one point for each pair of values. Putting revision time on the vertical axis swaps the roles of the variables, and bars belong to a different type of chart.
4.

Medium·Calculate[2 marks]

A regression line is y=0.8x+12y=0.8x+12y=0.8x+12. Calculate the predicted value of yyy when x=35x=35x=35.
Show answer and explanation

Answer: B · Worked explanation

Substitute: y=0.8×35+12=28+12=40y=0.8\times35+12=28+12=40y=0.8×35+12=28+12=40. The value 28 comes from leaving out the intercept 12. The value 47.8 comes from adding 0.8, 35 and 12 instead of multiplying the gradient by xxx, and 28.75 comes from rearranging the equation the wrong way round.
5.

Medium·Identify[1 mark]

A regression line for ice creams sold yyy against temperature xxx in ∘C^{\circ}\mathrm{C}∘C is y=12x−90y=12x-90y=12x−90. Identify the correct interpretation of the gradient.
Show answer and explanation

Answer: B · Worked explanation

The gradient is the average change in yyy for each increase of 1 in xxx, so 12 is the extra ice creams per 1 ∘C1\,^{\circ}\mathrm{C}1∘C. The intercept, not the gradient, gives the predicted value at 0 ∘C0\,^{\circ}\mathrm{C}0∘C, which is the most tempting wrong reading here. Reversing the variables or using percentages changes the meaning.
6.

Medium·Determine[1 mark]

Determine which correlation coefficient shows the strongest linear correlation.
Show answer and explanation

Answer: D · Worked explanation

Strength depends on the size of rrr, ignoring the sign. The value -0.8 has size 0.8, which is the largest of the four. A student may choose 0.7 because it is the biggest value, but a negative sign only gives the direction and does not make the correlation weaker.
7.

Medium·Identify[1 mark]

A regression line is based on data with xxx from 10 to 40. Identify the prediction that is least reliable.
Show answer and explanation

Answer: A · Worked explanation

The value x=60x=60x=60 lies outside the range 10 to 40, so predicting from it is extrapolation. The pattern may not continue beyond the data. The values 15, 25 and 38 all lie inside the range, so they are interpolation. The value 38 is near the edge of the data but is still inside it.
8.

Hard[2 marks]

A student finds r=0.02r=0.02r=0.02 for data that lie close to a clear curved pattern. Which conclusion is best?
Show answer and explanation

Answer: A · Worked explanation

The coefficient rrr measures linear correlation only, so a curve can give a value near 0 even when the variables are closely related. Concluding that there is no relationship at all is the tempting error. A straight regression line would fit curved data badly, so its predictions would not be accurate.
9.

Hard[2 marks]

A regression line is y=−2.5x+90y=-2.5x+90y=−2.5x+90, based on data with xxx from 4 to 20. A prediction is made for x=8x=8x=8. Which statement is correct?
Show answer and explanation

Answer: C · Worked explanation

Substitute: y=−2.5×8+90=−20+90=70y=-2.5\times8+90=-20+90=70y=−2.5×8+90=−20+90=70. Since 8 lies between 4 and 20, this is interpolation and is reliable. The value 110 comes from treating −2.5×8-2.5\times8−2.5×8 as +20+20+20. Calling 8 outside the range is false, and a negative gradient does not make a prediction unreliable.
10.

Hard·Determine[2 marks]

A regression line y=2x+3y=2x+3y=2x+3 is found from data in which the mean of the xxx values is 5. Determine the mean of the yyy values.
Show answer and explanation

Answer: C · Worked explanation

The regression line passes through the mean point, so the mean of yyy is found by substituting x=5x=5x=5: y=2×5+3=13y=2\times5+3=13y=2×5+3=13. The value 10 leaves out the intercept. The value 8 adds 5 and 3 without using the gradient, and 16 comes from doubling the sum of 5 and 3.

Keep going

Next topic4.5 Probability conceptsPrevious topic4.3 Measures of central tendency and spread

More in Topic 4 · Statistics and probability

  1. 4.1Sampling conceptsNotes · 10 questions
  2. 4.2Presenting dataNotes · 10 questions
  3. 4.3Measures of central tendency and spreadNotes · 10 questions
  4. 4.4Correlation and regressionNotes · 10 questions
  5. 4.5Probability conceptsNotes · 10 questions
  6. 4.6Combined events and diagramsNotes · 10 questions
  7. 4.7Discrete random variablesNotes · 10 questions
  8. 4.8Binomial distributionNotes · 10 questions
  9. 4.9Normal distributionNotes · 10 questions

All IB Mathematics: Applications and Interpretation topics →

Draft: written by Scribe and checked automatically, not yet by a subject reviewer.

Practice questions are original, written by Scribe and checked automatically for correctness.

Topic codes follow the official numbering. Not endorsed by IB Diploma Programme or any exam board.

On this page

0/5 read

  1. 1A scatter diagram shows how two variables are related
  2. 2Correlation describes the direction and strength of a pattern
  3. 3Pearson’s r gives a number for the strength of linear correlation
  4. 4A regression line models the trend between two variables
  5. 5Predictions are reliable only inside the range of the data
  6. Check your recall
  7. Practice: 10 questions
All coursesScribeHow it worksPricingPrivacyTerms

Notes and questions are written by Scribe in our own words. Topic codes follow the official course numbering so you can find your place. Not produced or endorsed by the IB, College Board, AQA, OCR, Pearson Edexcel or any exam board.

© 2026 Scribe

Test score against revision time

Test score (marks)0246830405060708090Revision time (hours)
  • Regression line
  • Data points