Revision notes

Chapter 13 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

Grouped data and the mean by the direct method

Mean x̄ = Σfᵢxᵢ ÷ Σfᵢ. For grouped data, xᵢ is the class mark: class mark = (lower limit + upper limit) ÷ 2.

Scores of 20 students
Score (x)456789
Students (f)235442

Direct method for the mean of grouped data

  1. Find class marks xᵢ = (lower + upper) ÷ 2 for each class
  2. Multiply fᵢ × xᵢ for each class
  3. Add the columns Find Σfᵢ and Σfᵢxᵢ
  4. Divide x̄ = Σfᵢxᵢ ÷ Σfᵢ
Time spent on homework by 40 students
Time (minutes)0-2020-4040-6060-8080-100
Number of students4101484
Working table
ClassfClass mark xfx
0-2041040
20-401030300
40-601450700
60-80870560
80-100490360
Total401960

Key takeaways: the class mark represents a whole class; the direct method is Σfx ÷ Σf; a value equal to a shared limit goes into the class that starts with it; always add a total row and check that your mean lies within the classes.

Read the full lesson

Lesson 2

Mean of grouped data: assumed mean and step-deviation methods

Assumed mean method: x̄ = a + Σfᵢdᵢ ÷ Σfᵢ. Step-deviation method: x̄ = a + h × (Σfᵢuᵢ ÷ Σfᵢ), where uᵢ = (xᵢ − a) ÷ h and h is the class size.

Class mark xfd = x − 50fd
104−40−160
3010−20−200
501400
70820160
90440160
Total40−40
Bills of 50 households, a = 450, h = 100
Bill (₹)fxu = (x − 450) ÷ 100fu
200-3004250−2−8
300-40012350−1−12
400-5001545000
500-60010550110
600-7009650218
Total508

Three methods for the mean

  • Direct
    • x̄ = Σfx ÷ Σf
    • Best when class marks are small
    • Most multiplication
  • Assumed mean
    • d = x − a
    • x̄ = a + Σfd ÷ Σf
    • Good for large class marks
  • Step deviation
    • u = (x − a) ÷ h
    • x̄ = a + h × Σfu ÷ Σf
    • Easiest when all deviations share the factor h
All three give the same mean.

Key takeaways: pick a central class mark as a; keep the signs of deviations; in step deviation, multiply by h at the end; all three methods give the same answer, so a quick check with another method catches errors; for a missing frequency, write the mean equation and solve it.

Read the full lesson

Lesson 3

Mode of grouped data

Mode = l + [(f₁ − f₀) ÷ (2f₁ − f₀ − f₂)] × h, where l = lower limit of the modal class, h = class size, f₁ = frequency of the modal class, f₀ = frequency of the class before it, f₂ = frequency of the class after it.

Finding the mode of grouped data

  1. Find the modal class The class with the highest frequency
  2. Read the values l, h, f₁, f₀ (class before), f₂ (class after)
  3. Substitute Into l + [(f₁ − f₀) ÷ (2f₁ − f₀ − f₂)] × h
  4. Check The mode must lie inside the modal class
Books read0-44-88-1212-1616-20
Students6111463
Height (cm)10-2020-3030-4040-5050-60
Plants5916128
Mean and mode answer different questions
MeasureWhat it tells youExample
MeanThe balance point of all valuesAverage marks of a class
ModeThe most common valueThe shoe size a shop should stock most

Key takeaways: the modal class is the class with the highest frequency, not the highest class mark; f₀ is the class before and f₂ the class after; use f₀ = 0 or f₂ = 0 at the ends of the table; the answer must fall inside the modal class, which is a quick check on your working.

Read the full lesson

Lesson 4

Cumulative frequency and the median of grouped data

Time spent on homework by 40 students
Time (minutes)0-2020-4040-6060-8080-100
Number of students4101484
Both types of cumulative frequency for the homework data
Less thanCumulative frequencyMore than or equal toCumulative frequency
204040
404 + 10 = 142040 − 4 = 36
6014 + 14 = 284036 − 10 = 26
8028 + 8 = 366026 − 14 = 12
10036 + 4 = 408012 − 8 = 4

Median = l + [(n/2 − cf) ÷ f] × h, where l = lower limit of the median class, n = number of observations, cf = cumulative frequency of the class BEFORE the median class, f = frequency of the median class, h = class size.

Finding the median of grouped data

  1. Add a cf column Running totals of the frequencies
  2. Find n/2 Half the total number of observations
  3. Find the median class First class whose cf is greater than n/2
  4. Read l, cf, f, h cf belongs to the class before the median class
  5. Substitute l + [(n/2 − cf) ÷ f] × h
Bill (₹)200-300300-400400-500500-600600-700
f41215109
cf416314150

Key takeaways: cumulative frequency is a running total; the median class is the first with cf greater than n/2; in the formula, cf is the cumulative frequency of the class before the median class and f is the median class's own frequency; the median must lie inside the median class.

Read the full lesson

Lesson 5

Choosing mean, median or mode, and the empirical relation

Which measure to use

  • Mean
    • Uses every observation
    • Good for comparing groups
    • Pulled by very large or very small values
  • Median
    • The middle value
    • Not affected much by extreme values
    • Good for incomes, wages, house prices
  • Mode
    • The most frequent value
    • Good for 'most popular' questions
    • e.g. most sold size or colour
SituationBest measureWhy
Average marks to compare two sectionsMeanEvery student's mark counts
Typical salary in a company with a few very high salariesMedianExtreme salaries do not drag it up
Which school uniform size to order mostModeWe want the most common size

For many moderately skewed distributions: 3 Median = Mode + 2 Mean. It is an approximate relation found from experience, not an exact law.

Marks1-1011-2021-3031-40
Students37128

Key takeaways: the mean uses all values but is pulled by extremes; the median resists extremes; the mode answers 'most common'; 3 Median = Mode + 2 Mean links the three approximately; make inclusive classes continuous with ±0.5 before using the median or mode formula; to find a missing frequency, set up the formula as an equation and check the median class afterwards.

Read the full lesson

Privacy · Terms · Refunds · Delivery