Skip to content
MathClicksIGCSE← All notes Cambridge IGCSE® Mathematics 0580 Extended Chapter 12 — Averages and Measures of Spread

12.3  Averages for Grouped Data

Estimating the mean of grouped continuous data with midpoints, finding the modal class and the class containing the median — and saying ‘estimate’ at the right moments.

What grouping does to the data

Continuous data — heights, times, masses — is almost always presented in classes written with inequalities, like 150 ≤ h < 160. Grouping makes a big data set readable, but it comes at a price: once a height is filed under 150 ≤ h < 160, nobody knows whether it was 150.2 or 159.8. The individual values are gone.

Key idea Because the exact values are lost, every average you calculate from grouped data is an estimate. The exam expects the word: write “estimate of the mean”, “modal class” and “the class containing the median” — not “mean”, “mode” and “median”.

This page works with the heights of 40 students:

Height h (cm)Frequency f
130 ≤ h < 1405
140 ≤ h < 15012
150 ≤ h < 16018
160 ≤ h < 1705
Total40

Each class stands in for its midpoint

130 140 150 160 170 135 145 155 165 every value in a class is treated as if it sat at the middle height (cm)
Watch out Classes must not overlap. 130–140, 140–150 is ambiguous (where does exactly 140 go?), which is why the syllabus writes 130 ≤ h < 140, 140 ≤ h < 150 — the boundary value belongs to the class where it meets a ≤.

The estimated mean

The method is exactly 12.2’s Σfx ÷ Σf with one extra first step: since the true values are unknown, use each class’s midpoint as the stand-in value x. The midpoint is the mean of the two boundaries.

estimate of mean = Σ(midpoint × f)Σf midpoint = (lower boundary + upper boundary) ÷ 2
Example 1Calculate an estimate of the mean height of the 40 students in the table above.
1
Find each midpoint. (130 + 140) ÷ 2 = 135   (140 + 150) ÷ 2 = 145
(150 + 160) ÷ 2 = 155   (160 + 170) ÷ 2 = 165
2
Multiply each midpoint by its frequency and total the column. 135 × 5 = 675
145 × 12 = 1740
155 × 18 = 2790
165 × 5 = 825
Σ(mp × f) = 675 + 1740 + 2790 + 825 = 6030
3
Divide by the total frequency. estimate of mean = 6030 ÷ 40 = 150.75
estimate of the mean = 150.75 cm
Exact division, estimated answer The arithmetic 6030 ÷ 40 is exact — what makes the result an estimate is the midpoints standing in for the lost values. Say “estimate of the mean” in your answer line.
Exam tip The word “estimate” in the question is your instruction to use midpoints — and using anything else (class boundaries, class widths) scores zero. One midpoint error poisons the whole column, so write the midpoints into the table before touching the calculator.

Grouped-mean calculator

Set where the classes start, their common width and the four frequencies — the midpoint column, totals, estimated mean, modal class and median class all update live.

Working backwards

Example 3Times are grouped as 0 ≤ t < 10, 10 ≤ t < 20, 20 ≤ t < 30 with frequencies 6, x and 4. An estimate of the mean is 14 minutes. Find x.
1
Midpoints are 5, 15 and 25. Write both totals in terms of x. Σ(mp × f) = 5(6) + 15x + 25(4) = 130 + 15x
Σf = 6 + x + 4 = 10 + x
2
Set the estimated mean equal to 14 and clear the fraction. (130 + 15x)/(10 + x) = 14
130 + 15x = 14(10 + x) = 140 + 14x
3
Solve and check. 15x − 14x = 140 − 130  →  x = 10
check: (130 + 150) ÷ 20 = 280 ÷ 20 = 14 ✓
x = 10
Example 4Two groups of 20 runners each record their 5 km times. Group A: estimated mean 26.5 min, times spread from 18 to 41 min. Group B: estimated mean 26.5 min, times spread from 24 to 30 min. Compare the two groups.
1
Compare an average, in context. The estimated means are equal (26.5 min) — on average the groups are equally fast.
2
Compare the spread, in context. Group A’s range ≈ 23 min, Group B’s ≈ 6 min — Group B’s times are far more consistent.
Same average speed; Group B is much more consistent than Group A.
The two-mark comparison sentence One comment about the average + one comment about the spread, both in the story’s language. “A has a bigger range” alone is only half the marks.

More worked examples

Example 5Waiting times: 0 ≤ t < 5 (f = 4), 5 ≤ t < 15 (f = 10), 15 ≤ t < 30 (f = 6). The classes have different widths. Estimate the mean waiting time.
Different widths are no problem for the mean — each class still stands in for its own midpoint. (Unequal widths only change how you draw the data: that is the frequency-density story of 20.1.)
1
Midpoints: (0+5)/2 = 2.5, (5+15)/2 = 10, (15+30)/2 = 22.5.
2
Multiply and total. 2.5 × 4 = 10   10 × 10 = 100   22.5 × 6 = 135
Σ = 245,  Σf = 20
3
estimate of mean = 245 ÷ 20 = 12.25
estimate of the mean = 12.25 minutes
Example 6For the waiting-times data of Example 5, find the class containing the median, and explain why the exact median cannot be found.
1
n = 20: the median is the mean of the 10th and 11th values. position = (20 + 1) ÷ 2 = 10.5
2
Running totals: 4, then 14. Positions 5–14 are in the second class. 4 < 10.5 ≤ 14  →  median lies in 5 ≤ t < 15
3
Why only the class? Grouping destroyed the individual times — the 10th and 11th values are known to be somewhere between 5 and 15 minutes, but not where.
median lies in 5 ≤ t < 15; the raw values are lost, so only the class is known

Your turn

Practice set

  1. Write down the midpoints of the classes 20 ≤ m < 30, 30 ≤ m < 40 and 40 ≤ m < 50.
  2. Masses 0 ≤ m < 10, 10 ≤ m < 20, 20 ≤ m < 30 have frequencies 3, 5, 2. Calculate an estimate of the mean mass.
  3. For the table in question 2, write down the modal class.
  4. For the table in question 2, find the class containing the median.
  5. A student says: “My answer to question 2 is the mean.” What one word is missing, and why does it matter?

  1. 25, 35 and 45 — each is (lower + upper) ÷ 2.
  2. Midpoints 5, 15, 25. Σ(mp × f) = 15 + 75 + 50 = 140, Σf = 10 → 140 ÷ 10 = 14 (an estimate).
  3. Largest frequency is 5 → modal class 10 ≤ m < 20.
  4. n = 10: median is the mean of the 5th and 6th values. Running totals 3, 8 — both positions fall in 10 ≤ m < 20.
  5. The word “estimate”. The true values were lost when the data was grouped, so midpoints stand in for them — the answer cannot claim to be exact.

Key points to remember

  • Grouping loses the raw values, so every answer is an estimate — and the word earns a mark.
  • Midpoint = (lower + upper) ÷ 2; the estimated mean is Σ(midpoint × f) ÷ Σf.
  • Write the midpoints into the table first — one midpoint slip wrecks the whole column.
  • Answer with the modal class and the class containing the median, each written in full inequality notation — never a single number.
  • Unequal class widths change nothing for the mean; they matter when drawing (frequency density, 20.1).
  • Comparing two data sets = one sentence about the average + one about the spread, in context.

Where next?

✅ Mark scheme All notes

Progress is saved on this device only and appears on the notes home page.