CSEC Mathematics · statistics
Measures of Dispersion: Range, IQR, and Semi-IQR
Before you start
Measures of central tendency (mean, median, mode) tell us where the centre of a data set lies. To find the median, you arrange the data in ascending order and locate the middle value.
Builds on: Measures of Central Tendency
1. The Range
While averages tell you what is typical, measures of dispersion describe how spread out the values are.
The simplest measure of spread is the range. It is the difference between the largest value and the smallest value in a data set:
The range gives a quick snapshot of the entire spread. However, it has one major drawback: it depends only on the two most extreme values. If a single value is unusually large or small (an outlier), the range becomes misleadingly large.
In CSEC multiple-choice and structured questions, you may also be asked to work backwards: if you are given the highest value and the range, you can find the lowest value using:
Worked example
A supervisor at a bakery in Port of Spain records the daily production of loaves of bread over six days: 240,310,275,450,290,360.
(a) Determine the range of daily bread production.
(b) If an oven broke down on a seventh day and only 120 loaves were baked, calculate the new range.
- Identify the highest and lowest values in the original six days: Highest=450, Lowest=240.
- Calculate the original range: Range=450−240=210 loaves.
- Include the seventh day (120 loaves): the new lowest value is now 120, while the highest remains 450.
- Calculate the new range: New Range=450−120=330 loaves.
Answer: (a) 210 loaves; (b) 330 loaves
Quick check
A farmer in St. Elizabeth records the weights of watermelons. The heaviest watermelon weighs 14.6 kg, and the range of weights is 6.8 kg. What is the weight of the lightest watermelon?
2. Quartiles and the Interquartile Range (IQR)
Because the range is easily distorted by extreme values, statisticians often look at the spread of the middle half of the data instead.
When data values are arranged in ascending order, quartiles divide the data into four equal parts:
- **Lower quartile (Q1):** the value one-quarter (25%) of the way into the ordered list.
- **Median (Q2):** the middle value (50% of the data).
- **Upper quartile (Q3):** the value three-quarters (75%) of the way into the ordered list.
To find the quartiles for raw data:
1. Write the values in order from least to greatest.
2. Find the median (Q2), which divides the data into a lower half and an upper half.
3. Find the middle of the lower half; this is Q1.
4. Find the middle of the upper half; this is Q3.
The interquartile range (IQR) is the difference between the upper quartile and the lower quartile:
The IQR measures the spread of the middle 50% of the data and is unaffected by extreme outliers.
Worked example
The scores obtained by 10 students in a Mathematics mock test (out of 50) were:
Determine:
(a) the lower quartile (Q1)
(b) the upper quartile (Q3)
(c) the interquartile range (IQR)
- Arrange the 10 scores in ascending order: 14,18,20,25,28,30,33,38,41,45.
- Identify the two halves: the lower 5 values are 14,18,20,25,28 and the upper 5 values are 30,33,38,41,45.
- Find Q1: the middle value of the lower half is the 3rd value, so Q1=20.
- Find Q3: the middle value of the upper half is the 8th value, so Q3=38.
- Calculate the interquartile range: IQR=Q3−Q1=38−20=18.
Answer: (a) Q1=20; (b) Q3=38; (c) IQR=18
Quick check
For the data set: 8,12,15,17,21,24,29, calculate the interquartile range.
3. The Semi-Interquartile Range
The semi-interquartile range (sometimes referred to as the quartile deviation) is simply half of the interquartile range:
The prefix 'semi' means half.
### Comparing Data Sets
Measures of dispersion allow us to compare two distributions:
- A larger IQR or semi-IQR indicates that the data values are more spread out (less consistent).
- A smaller IQR or semi-IQR indicates that the data values cluster more closely around the median (more consistent).
When CSEC asks which set of data is 'more consistent' or 'more spread out', compare their ranges or IQRs and state your conclusion clearly.
Worked example
Two sprinters, Devon and Ravi, each ran ten 100 m trial races. Their ordered times (in seconds) are:
Devon: 11.2,11.4,11.5,11.8,12.0,12.1,12.4,12.6,12.9,13.5
Ravi: 11.6,11.7,11.8,11.9,12.0,12.1,12.2,12.2,12.4,12.5
(a) Calculate the semi-interquartile range for each runner.
(b) State which runner was more consistent, giving a reason.
- For Devon (10 values): lower half is 11.2,11.4,11.5,11.8,12.0, so Q1=11.5. Upper half is 12.1,12.4,12.6,12.9,13.5, so Q3=12.6.
- Devon's IQR=12.6−11.5=1.1 s. Devon's semi-IQR=21.1=0.55 s.
- For Ravi (10 values): lower half is 11.6,11.7,11.8,11.9,12.0, so Q1=11.8. Upper half is 12.1,12.2,12.2,12.4,12.5, so Q3=12.2.
- Ravi's IQR=12.2−11.8=0.4 s. Ravi's semi-IQR=20.4=0.2 s.
- Compare the values: Ravi has a smaller semi-interquartile range (0.2 s<0.55 s), meaning his times are more clustered and therefore more consistent.
Answer: (a) Devon: 0.55 s, Ravi: 0.2 s; (b) Ravi is more consistent because his semi-interquartile range is smaller.
Quick check
A data set has a lower quartile of 32 and an upper quartile of 58. What is the semi-interquartile range?
Common mistakes
- Leaving the range as a pair of numbers (such as '15−42') instead of subtracting to give a single value (42−15=27).
- Finding quartiles before ordering the data from least to greatest.
- Dividing by 4 instead of 2 when calculating the semi-interquartile range. Remember that 'semi' means half, so you divide the IQR by 2.
In the exam
- Always write out the ordered list of data values on your exam script. CSEC examiners award method marks for ordering the data and clearly identifying Q1 and Q3.
- Include appropriate units in your final answers (such as cm, kg, or \$) when the question provides them.
- For Paper 1 reverse-range questions, check your answer by subtracting your calculated lowest value from the given highest value to see if it yields the given range.
Key terms
- Measures of Dispersion
- Statistical values that describe the spread or variability of a data set.
- Range
- The difference between the highest value and the lowest value in a data set.
- Lower Quartile (Q1)
- The value that cuts off the lowest 25% of the ordered data (the 25th percentile).
- Upper Quartile (Q3)
- The value that cuts off the lowest 75% of the ordered data (the 75th percentile).
- Interquartile Range (IQR)
- The difference between the upper quartile and the lower quartile: Q3 - Q1.
- Semi-Interquartile Range
- Half of the interquartile range, given by (Q3 - Q1) / 2.
Practice
Easier to harder. Use paper for your working.
Practice 1
The heights, in centimetres, of nine mango saplings measured at an agricultural station in Guyana are:
Determine the range of the heights.
Practice 2
Among a group of workers at a factory in Kingston, the highest paid employee earns a weekly wage of \134.50.Iftherangeoftheweeklywagesis\38.20, what does the lowest paid employee receive?
Practice 3
The number of crates of citrus fruit picked each day over a 10-day period on a citrus estate in Dominica were:
Calculate the semi-interquartile range of the crates picked.
Now try real past-paper questions
2 Paper 2 questions and 3 Paper 1 multiple-choice on this topic. Quelpr marks your working point by point, like an examiner.
- Mathematics Q7 7(a)(iii) · 2 marksThe marks obtained by 10 students in a test, scored out of 60, are shown below: 29, 38, 26, 42, 38, 45, 35, 37, 38, 31. For the data above, determine the interquartile range.
- Mathematics Q7 7(b) · 2 marksUsing the raw scores, determine the range for the data.
Finished the lesson?
0 of 6 checks right on this device.
Read more
- Collins - Concise Revision Course for CSEC Mathematics, pp. 410, 411
- Mathematics for CSEC, pp. 524, 533
- CSEC Maths Study Guide - Maths Crash Course, p. 112
- introductory-statistics-2e_-_WEB, pp. 100, 108
- CXC Study Guide - Mathematics for CSEC, pp. 72, 73