Danulearn Open Danulearn
Unit 3

Statistics

πŸ“—Introduction
  • Statistics deals with the collection, organisation, presentation, analysis and interpretation of numerical data.
  • An average alone does not show how spread out the data are, so in this unit you measure dispersion, compare data sets with relative measures, read skewness from frequency curves, and choose good samples.

Each solution names the textbook formula first and then works one short step at a time, with a table for the deviations wherever there are many numbers.

🎯 Learning Outcomes
  • Describe absolute and relative dispersion and their interpretation.
  • Calculate the range, inter-quartile range, mean deviation, quartile deviation, variance and standard deviation.
  • Calculate and compare coefficients of range, quartile deviation, mean deviation and variation.
  • Determine skewness from the mean, median and mode and from Pearson's and Bowley's coefficients.
  • Grasp basic concepts about sampling techniques.
  • Appreciate the value of statistics in real life.
3.1  Measures of Absolute Dispersions
  • A measure of dispersion shows how much numerical data spread about an average.
  • An absolute measure of dispersion (range, inter-quartile range, mean deviation, standard deviation) has the same unit as the data, for example metres or kilograms.
  • A relative measure of dispersion (coefficient of range, of quartile deviation, of mean deviation, coefficient of variation) has no unit, so it can compare data sets measured in different units.
3.1.1 Range and Inter-quartile Range
  • The range of ungrouped data is R = L βˆ’ S, where L is the largest and S the smallest value.
  • For grouped data, R = upper class boundary of the highest class βˆ’ lower class boundary of the lowest class.
  • The range is simple to compute, but it depends only on the two extreme values.
  • The inter-quartile range is IQR = Q₃ βˆ’ Q₁ (Definition 3.3).
  • For ungrouped data with n items, Q_k is the (k(n + 1)/4)th item if n is odd and the item if n is even.
  • For grouped data, Q_, where L is the lower boundary of the quartile class, cf the cumulative frequency before it, f its frequency and w the class width.
  • The IQR uses only the middle 50% of the data.
  • The range and the inter-quartile range answer the same question in two ways.
  • The range uses only the two extreme values, so one unusual value can make it very large; the inter-quartile range uses the middle half of the data and ignores the extremes.
Example
1
For 3, 5, 6, 8, 9, 11, 30 the range is
30 βˆ’ 3 = 27, but
n = 7,
so Q₁ is the 2nd value 5 and Q₃ is the 6th value 11, and the IQR is
11 βˆ’ 5 = 6, which describes the typical spread much better.
πŸ”’
The rest of Unit 3 is in the Danulearn app

Read the full notes for all 4 sections, worked examples and figures, plus 33 exercises with step-by-step solutions, the Short Note and the unit review.

πŸ“‘ Contents

  1. 3.1Measures of Absolute DispersionsPreview
  2. 3.2Relative DispersionsπŸ”’
  3. 3.3Use of Frequency CurvesπŸ”’
  4. 3.4Sampling TechniqueπŸ”’

✍️ Practice questions

5 questions from the Unit 3 quiz. Choose an answer, then check it.

  1. 1

    The range of a data set is calculated as:

    • AThe difference between the highest and lowest values (upper boundary minus lower boundary for grouped data)
    • BThe middle value when data is ordered
    • CThe mean of all values
    • DThe most frequently occurring value
    Show answer

    A The difference between the highest and lowest values (upper boundary minus lower boundary for grouped data)

  2. 2

    A key limitation of the range as a measure of dispersion is that it:

    • ACannot be computed for grouped data
    • BConsiders all values in the data set equally
    • CIs always equal to zero
    • DDepends only on the extreme (highest and lowest) values and ignores the values in between
    Show answer

    D Depends only on the extreme (highest and lowest) values and ignores the values in between

  3. 3

    Mean deviation of a data set is defined as:

    • AThe difference between the maximum and minimum values
    • BThe square root of the variance
    • CThe most common value in the data set
    • DThe sum of all deviations (in absolute value) from the mean, divided by the number of items
    Show answer

    D The sum of all deviations (in absolute value) from the mean, divided by the number of items

  4. 4

    When calculating mean deviation, each deviation from the mean is taken as an absolute value mainly because:

    • AIt simplifies multiplication
    • BIt has no particular reason
    • CNegative deviations would otherwise cancel out positive deviations, giving a misleading sum of zero
    • DNegative numbers are not allowed in statistics
    Show answer

    C Negative deviations would otherwise cancel out positive deviations, giving a misleading sum of zero

  5. 5

    The first quartile (Q₁) of a data set corresponds to the value below which approximately what percentage of the data falls?

    • A10%
    • B25%
    • C50%
    • D75%
    Show answer

    B 25%