Revision notes

Chapter 6 Statistics: Foundation

The key points, rules to remember, tables and diagrams from all 5 lessons, on one page for quick revision. To keep a copy, use your browser's Print and choose "Save as PDF".

Lesson 1

Mean of grouped data: the direct method

Direct method: X̄ = Σxᵢfᵢ / Σfᵢ, where xᵢ is the class mark, fᵢ the frequency and Σfᵢ = N.

— Mean of grouped data

Direct method step by step

  1. Column 1: classes As given in the table.
  2. Column 2: class marks xᵢ Middle of each class.
  3. Column 3: frequencies fᵢ Add them to get N = Σfᵢ.
  4. Column 4: products xᵢfᵢ Add them to get Σxᵢfᵢ.
  5. Divide Mean = Σxᵢfᵢ ÷ Σfᵢ.
40 students and their daily homework time in minutes (invented for practice)
Class (minutes)Class mark xᵢFrequency fᵢxᵢfᵢ
0-2010440
20-403010300
40-605014700
60-80708560
80-100904360
TotalΣfᵢ = 40Σxᵢfᵢ = 1960

Key takeaways: the class mark represents every score in its class, which is why the grouped mean is approximate. Make a four-column table, add the frequencies and the products, and divide. Check that the mean lies within the range of the data and near the classes with the most scores.

Read the full lesson

Lesson 2

Assumed mean and step deviation methods

Assumed mean method: dᵢ = xᵢ − A, d̄ = Σfᵢdᵢ / Σfᵢ, X̄ = A + d̄. Step deviation method: uᵢ = dᵢ / g, ū = Σfᵢuᵢ / Σfᵢ, X̄ = A + ū × g.

— Shortcut methods for the mean
Assumed mean A = 225
Classxᵢdᵢ = xᵢ − 225fᵢfᵢdᵢ
100-150125−1006−600
150-200175−5014−700
200-250225 (A)0200
250-300275507350
300-3503251003300
Total50−650

Three methods for the mean of grouped data

  • Direct
    • Uses xᵢfᵢ
    • Simple idea
    • Large products
  • Assumed mean
    • Uses dᵢ = xᵢ − A
    • Smaller numbers, some negative
    • X̄ = A + d̄
  • Step deviation
    • Uses uᵢ = dᵢ ÷ g
    • Smallest numbers
    • X̄ = A + ū × g

Key takeaways: measuring from an assumed mean and dividing by a common factor shrinks the numbers without changing the mean. X̄ = A + d̄ and X̄ = A + ū × g. The value chosen for A never changes the final mean.

Read the full lesson

Lesson 3

Median of grouped data

Median = L + [(N/2 − cf) / f] × h, where L = lower limit of the median class, N = total frequency, cf = cumulative frequency of the class before the median class, f = frequency of the median class, h = class width.

— Median of grouped data

Finding the median of grouped data

  1. Make classes continuous Only if there are gaps.
  2. Write 'less than' cumulative frequencies Keep adding the frequencies down the table.
  3. Find N/2 The position of the middle score.
  4. Find the median class The first class whose cumulative frequency reaches N/2.
  5. Apply the formula Read L, cf, f and h, then calculate.
Invented marks for practice
MarksFrequencyCumulative frequency (less than)
0-1055
10-20914
20-301630
30-402252
40-501870
50-601080

Key takeaways: use continuous classes, write 'less than' cumulative frequencies, locate N/2, and read L, cf, f and h for the median class. cf belongs to the class just before the median class, not to the median class itself. The median of grouped data is an estimate.

Read the full lesson

Lesson 4

Mode of grouped data and choosing a measure

Mode = L + [(f₁ − f₀) / (2f₁ − f₀ − f₂)] × h, where L = lower limit of the modal class, f₁ = its frequency, f₀ = frequency of the class before it, f₂ = frequency of the class after it, h = class width.

— Mode of grouped data

Finding the mode

  1. Make classes continuous if needed Subtract and add 0.5 when there are gaps of 1.
  2. Pick the modal class Greatest frequency f₁.
  3. Read f₀ and f₂ Neighbours before and after; 0 if there is none.
  4. Substitute in the formula Work out the denominator 2f₁ − f₀ − f₂ carefully.

Mean, median and mode: when to use which

  • Mean
    • Uses every score
    • Comparing overall performance of groups
    • Affected by extreme values
  • Median
    • The middle score
    • Splitting a group into two equal halves
    • Not affected by a few extreme values
  • Mode
    • The most frequent value
    • Most popular size, colour or item
    • Works even for non-number data such as colours

Key takeaways: the modal class has the greatest frequency; use f₀ = 0 or f₂ = 0 when a neighbour is missing. Mode = L + [(f₁ − f₀)/(2f₁ − f₀ − f₂)] × h. Choose the mean for overall comparison, the median to split into halves or when there are extreme values, and the mode for the most common choice.

Read the full lesson

Lesson 5

Histogram, frequency polygon and pie diagram

Ways of presenting data

  • Tabulation
    • Ungrouped
    • Grouped
  • Pictorial
    • Bar diagrams
    • Pie diagram
  • Graphical
    • Histogram
    • Frequency polygon
    • Line graph
Classes 10-20: 5, 20-30: 12, 30-40: 9, with extra classes at both ends
ClassClass markFrequencyPoint
0-10 (extra)50(5, 0)
10-20155(15, 5)
20-302512(25, 12)
30-40359(35, 9)
40-50 (extra)450(45, 0)

Central angle of a sector θ = (number of scores in the component ÷ total number of scores) × 360°. For a percentage p, θ = p/100 × 360° = 3.6p°.

— Pie diagram
A family's monthly spending, invented for practice
ItemPercentageCentral angle
Food35%35/100 × 360 = 126°
Rent25%90°
Education20%72°
Travel10%36°
Savings10%36°
Total100%360°

Key takeaways: a histogram uses touching rectangles on continuous classes; a frequency polygon joins (class mark, frequency) points and closes on the axis at both ends; a pie diagram uses central angles θ = (part ÷ total) × 360° that add to 360°. To read a pie diagram, use the proportion angle ÷ 360 = part ÷ total.

Read the full lesson

Privacy · Terms · Refunds · Delivery