4.3 Measures of central tendency and dispersion

4.3 Measures of central tendency and dispersion

IB Maths: Analysis and Approaches SL: Revision notes

Studying this course? Keep your progress in one place.

Key facts

  • Mean =∑xn=\frac{\sum x}{n}; the median is the middle of the ordered data; the mode is the most frequent value.
  • Grouped data: use mid-interval values; the result is an estimate. Modal class = highest frequency.
  • IQR =Q3−Q1=Q_3-Q_1; σ\sigma and σ2\sigma^2 come from technology.
  • y=ax+by=ax+b: the mean becomes axˉ+ba\bar x+b and the standard deviation becomes ∣a∣σ|a|\sigma.
  • With skewed data or an extreme value, prefer the median and IQR.

Mean, median and mode

The mean is the total divided by the number of values; the median is the middle of the ordered data; the mode is the most frequent.

For a frequency table the mean is ∑fx∑f\frac{\sum fx}{\sum f}. At SL the data set is treated as the whole population, so the booklet writes the mean as μ\mu.

The median is the (n+12)\left(\frac{n+1}{2}\right)th value once the data are in order; with an even nn take the mean of the two middle values. The mode may be more than one value, or none. Knowing the mean gives the total: total =nxˉ=n\bar x.

01234512345Value xFrequency f
Frequency table: x = 1 to 5 with f = 2, 5, 4, 3, 1. The mode is 2 (highest bar), n = 15, Σfx = 41, mean ≈ 2.73 and the median is the 8th value, 3.
  • Meanxˉ=∑xn\bar x=\dfrac{\sum x}{n}
  • Frequency tablexˉ=∑fx∑f\bar x=\dfrac{\sum fx}{\sum f}
  • Totalnxˉn\bar x

Worked example

Find the mean, median and mode of 3, 6, 6, 8, 9, 10.

The mean of 9 values is 7. A tenth value is added and the mean becomes 8. What is the new value?

Grouped data

Replace each value in a class by its mid-interval value, then use ∑fx∑f\frac{\sum fx}{\sum f}.

For a class such as 25≤t<3025\le t<30 the mid-interval value is 27.5. The answer is an estimate because it assumes values in each class are centred on that value. The modal class is the class with the highest frequency (used here only with equal class widths).

02468100 to <1010 to <2020 to <30ClassFrequency
Frequency of each class: the tallest bar is the modal class.

Worked example

Estimate the mean: 0≤t<100\le t<10 (frequency 4), 10≤t<2010\le t<20 (6), 20≤t<3020\le t<30 (10).

To estimate the mean of grouped data you divide ∑fx\sum fx by...

Measures of dispersion

Range uses the two extremes, the IQR the middle 50%, and the standard deviation a typical distance from the mean.

Dispersion measures how spread out data are. The standard deviation σ\sigma has the same units as the data; the variance is σ2\sigma^2, so σ=variance\sigma=\sqrt{\text{variance}} (not the other way round).

Find σ\sigma and the variance with technology only, entering frequencies or mid-interval values. At SL use the population standard deviation, labelled σx\sigma x on most calculators.

0204060803.9RangeIQRStandard deviationMeasure of spreadValue
  • Without 120
  • With 120
Data 38, 39, 41, 42, 44, 45, 46, 47, 48, 51 with and without an extra value of 120: the IQR barely changes, but range and standard deviation jump.

Range

Measures:
Largest −- smallest
Affected by an extreme value:
Yes

IQR

Measures:
Q3−Q1Q_3-Q_1: middle 50%
Affected by an extreme value:
No

Standard deviation

Measures:
Typical distance from the mean
Affected by an extreme value:
Yes

Which measure of spread is not affected by one extreme value?

Quartiles and technology

Different standard methods give slightly different quartiles, and IB markschemes accept them.

The lower quartile Q1Q_1 and upper quartile Q3Q_3 split the ordered data into quarters. For discrete data find them with technology. Some calculators exclude the median and take the median of each half; others interpolate.

For 38, 39, 41, 42, 44, 45, 46, 47, 48, 51, 120, one method gives Q1=41Q_1=41 and Q3=48Q_3=48; another gives 41.541.5 and 47.547.5.

405060708090100110120Q₁ = 41Median = 45Q₃ = 48120

Exclude the median

Q1Q_1:
41
Q3Q_3:
48

Interpolate

Q1Q_1:
41.5
Q3Q_3:
47.5

Your calculator gives a slightly different Q1Q_1 from the markscheme. What does that tell you?

Effect of constant changes

For y=ax+by=ax+b the mean transforms the same way, but the standard deviation only scales by ∣a∣|a|.

Adding bb shifts the data without changing the spread, so σy=∣a∣σx\sigma_y=|a|\sigma_x and the variance is σy2=a2σx2\sigma_y^2=a^2\sigma_x^2. The median and mode transform like the mean.

Temperatures with mean 18.4∘18.4^\circC and σ=3.5∘\sigma=3.5^\circC, converted by F=1.8C+32F=1.8C+32, have mean 65.12∘65.12^\circF and σ=6.3∘\sigma=6.3^\circF.

51015202530354020406080100xyMean (18.4, 65.12)F = 1.8C + 32
F = 1.8C + 32: the mean transforms the same way (18.4 °C becomes 65.12 °F), and the gradient 1.8 is the factor that scales the standard deviation.
  • Meanyˉ=axˉ+b\bar y=a\bar x+b
  • Standard deviationσy=∣a∣σx\sigma_y=|a|\sigma_x
  • Varianceσy2=a2σx2\sigma_y^2=a^2\sigma_x^2

Worked example

Temperatures have mean 18.4∘18.4^\circC and σ=3.5∘\sigma=3.5^\circC. Convert with F=1.8C+32F=1.8C+32.

Data have mean 10 and σ=2\sigma=2. Each value is changed by y=3x−5y=3x-5. What are the new mean and σ\sigma?

Choosing a measure

An extreme value pulls the mean and standard deviation towards it but barely moves the median and IQR.

For skewed data, or data with an extreme value, the median and IQR usually describe a typical value and the spread better. For roughly symmetric data the mean and standard deviation use all of the data.

01020304050MeanMedianMeasure of centreValue
  • Without 120
  • With 120
The same data with and without an extreme value of 120: the mean moves by about 7, the median by less than 1.

Skewed or extreme value

Centre:
Median
Spread:
IQR

Roughly symmetric

Centre:
Mean
Spread:
Standard deviation

Data: 4, 5, 5, 6, 6, 7, 60. Which measure of centre better describes a typical value?

Try an exam question

The data 5, 7, 7, 9, 12 have standard deviation 2.4. Each value xx is transformed to y=2x+3y=2x+3. Find the mean and standard deviation of the new data.

[3 marks]

That's the notes covered.

Carry on to the next subtopic.

Try a question

Find the mean number of books read.

1 mark, marked against the mark scheme

Revision notes