All lessons

Module 1: Describing data · Lesson 1.2 · about 20 min

The centre: mean, median and mode

The three averages, how to work each one out, and which to report: the mean for totals and budgets, the median for typical values with a long tail, the mode for categories.

Key points, meanings and formulas on one page: choose "Save as PDF" in the print box.

Module 1 · about 20 minutes · school maths. You’ll be able to work out the mean, median and mode, explain why they differ, and choose the right one for a report.

The mean shares the total out equally, the median is the middle person, and the mode is the most common value: three different questions, three different answers.

In everyday terms: seven friends split a restaurant bill. The mean is what each pays if they split it evenly. The median is what the friend in the middle of the price list ordered. The mode is the dish most people chose.

1. Why there are three averages

“Average” sounds like one number, but there are three common ones, and on real business data they can disagree wildly. Average house prices, salaries and order values are famous for this. Picking the wrong one is one of the easiest ways for a report to mislead, often by accident.

2. The mean

Add up all the values and divide by how many there are:

x‾=x1+x2+⋯+xnn=1n∑i=1nxi

x‾ (say “x bar”) is the mean of a sample; μ (mu) is the mean of a whole population. The mean has one property nothing else has: mean × count = total. That makes it the right average for budgets, forecasts and anything that is later added up.

Its weakness: every value pulls on it, so a single extreme value can drag it a long way.

3. The median

Sort the values and take the middle one. With an even number of values, take the mean of the two middle ones. Half the values are below the median and half above, however extreme the ends are.

Try it: drag the biggest pay to the right
mean (average)
median (middle value)
people earning less than the mean
The mean adds everything up and shares it out equally, so one huge value drags it along. The median is the middle person once everyone is lined up, so it ignores how extreme the ends are. For pay, house prices and anything with a long tail, the median describes a typical person better. Made-up pay.

Drag the biggest value. The mean chases it; the median hardly moves. For anything with a long tail (pay, prices, order values, time on site, delivery times), the median describes the typical case far better.

4. The mode

The most common value. It is the only average for categories (most common payment method, busiest day of the week) and is handy for counts (most customers buy exactly 1 item). For measurements with decimals, every value may be unique, so the mode is rarely useful there unless you first group values into bins.

5. Which one to report

Situation Report Why
Totals, budgets, forecasts Mean Mean × count rebuilds the total
Typical customer, house, salary, wait Median Not dragged by a few extremes
Categories, most popular option Mode The only one that works
Both matter (e.g. order value) Mean and median The gap between them shows the skew

A useful habit: when the mean and median are far apart, say so. “Mean order $61, median $38” tells a manager there are some very large orders worth looking at.

Mean x̄
Add everything up, divide by how many: the "equal share".
Median
Sort the values; the middle one. Half are below, half above.
Mode
The value (or category) that turns up most often.
Physical meaning
The mean is the balance point of a see-saw holding every value at its place; one heavy value far out tips it a long way. The median only cares about order, so a billionaire walking into a café changes the mean income enormously and the median not at all.

“The average customer spends the mean.” With a long tail, most customers spend less than the mean: in the worked example six of seven do. Report the median as “typical” and keep the mean for totals and budgets.

Watch it happen, one step at a time:

The data. Seven customers spent $12, $15, $15, $18, $22, $30 and $250.
Mean. Add: 362. Divide by 7: about $51.71, the equal share.
Median. Already sorted; the 4th of 7 values is the middle: $18.
Mode. $15 appears twice, more than any other: $15.
Why they differ. The $250 customer pulls the mean up; the median does not move. Six of seven customers spent below the mean.
Report. "Typical spend $18; one large order of $250." Use the mean (7 × $51.71 = $362) for the revenue forecast.
Maths and principle

Principle: the mean is the balance point of the data (where a ruler with the values as weights would balance); the median is the halfway point by count.

Equations: x‾=1n∑xi. The median is the value at position n+12 in sorted order.

A second way to see the difference: the mean is the number c that makes the total squared distance ∑(xi−c)2 smallest; the median makes the total plain distance ∑|xi−c| smallest. Squaring punishes big gaps heavily, which is why the mean chases outliers.

Try it: for 1, 2, 3, 4, 100, the mean is 22 and the median is 3. Which one is closer to most of the values? (The median, by a mile.)

6. Worked example

Made-up numbers. Seven customers’ spend in a week: $12, $15, $15, $18, $22, $30, $250.

  • Mean: total = 12 + 15 + 15 + 18 + 22 + 30 + 250 = 362. 362 ÷ 7 ≈ $51.71.
  • Median: already sorted; 7 values, so the middle is the 4th: $18.
  • Mode: $15 appears twice: $15.

Six of the seven customers spent less than the mean. “Average customer spend is $52” is true but describes nobody. “The typical customer spent $18, and one big customer spent $250” is the honest report. If the store wants next week’s revenue, though, the mean is still the number: 7 customers × $51.71 = $362.

7. Practice

  1. Find the mean, median and mode of 4, 8, 6, 5, 3, 8, 7, 9.
  2. Ten staff earn $40k each and the owner earns $400k. Work out the mean and median pay. Which would a recruiting ad likely quote?
  3. Which average would you use for (a) the most popular pizza topping, (b) typical time on a support call, (c) next quarter’s total units?
Answers
  1. Sum 50, n = 8, mean 6.25. Sorted 3, 4, 5, 6, 7, 8, 8, 9: median (6 + 7) ÷ 2 = 6.5. Mode 8.
  2. Mean (10 × 40 + 400) ÷ 11 ≈ $72.7k; median $40k. An ad might quote the mean because it sounds better, though 10 of 11 people earn $40k.
  3. (a) Mode. (b) Median (call times have a long tail). (c) Mean × number of periods.

Try it on your own data: the grouped data tool works out all three averages from a frequency table, and the CSV profiler shows the mean and median of every column in a file.

New words: mean, median, mode, sample mean x‾, population mean μ, outlier, long tail.

  • Mean = total ÷ count; it uses every value and is pulled by extremes.
  • Median = the middle value after sorting; it resists outliers and long tails.
  • Mode = the most common value; the only average for categories.
  • Typical value: median. Totals and budgets: mean. Categories: mode.

Check yourself

1Order values were $20, $22, $25, $28 and $400. Which average best describes a typical order?
2A shop sold 120 units over 30 days. Finance wants to forecast next month's total. Which average should they use?
3What is the mode of the payment methods card, card, cash, phone, card, cash?

Sources

Your ticks stay in this browser. Save them as a file on the course home.

Updated 2026-11-22. Numbers in the examples are made up to show the idea unless a source is given. Simulations run in your browser; nothing you type is sent anywhere.