CSEC Mathematics · statistics
Standard Deviation for Data Comparison
Before you start
You already know how to measure spread using the range and interquartile range (IQR), and how to measure the centre of a dataset using the mean.
1. What Standard Deviation Measures
The standard deviation (often written as s or σ) is a single number that measures how far data values are spread out around the mean.
Good news for CSEC: you do not have to calculate the standard deviation using long arithmetic! The syllabus only requires you to understand what it means and use it to compare datasets.
Key rules to remember:
- A smaller standard deviation means the values are tightly clustered close to the mean. The data has little spread and is more consistent.
- A larger standard deviation means the values are spread farther away from the mean. The data has greater variability.
- If the standard deviation is zero, there is no spread at all; every single score or measurement in the dataset is identical.
Worked example
Two Jamaican sprinters, Kemar and Andre, each ran six 100 m trials. Both sprinters finished with an identical mean time of 10.4 s. Kemar's times have a standard deviation of 0.08 s, while Andre's times have a standard deviation of 0.25 s. Which runner was more consistent, and what does this mean about their race times?
- Compare the standard deviations: Kemar's standard deviation (0.08 s) is smaller than Andre's (0.25 s).
- Interpret the smaller standard deviation: A smaller standard deviation means the times deviate less from the mean.
- Write the conclusion clearly: Kemar is the more consistent runner because his times are clustered closer to the average of 10.4 s, whereas Andre's times are more widely spread out.
Answer: Kemar was more consistent. His race times were clustered closer to the mean, showing less variation than Andre's.
Quick check
Five students in a study group each scored exactly 72 out of 100 on a mathematics test. What is the standard deviation of their scores?
2. Comparing Two Datasets Using Exam Keywords
When CSEC asks you to comment on or compare two distributions using standard deviation, CXC examiners look for specific vocabulary:
- spread or dispersion
- deviates
- mean
- consistent or variability
Always link your comment back to the context of the question (marks, heights, rainfall, or scores). Never just say 'Class A is bigger'. State clearly which group has values closer to the mean and which group has values more spread out.
| Measure | Class A | Class B |
|---|---|---|
| Mean Mark | 64 | 64 |
| Standard Deviation | 5.2 | 14.8 |
| Interpretation | Marks are concentrated near 64 (more consistent performance) | Marks are widely spread from 64 (greater variability in ability) |
Worked example
A poultry farmer in Guyana monitors the egg weights (in grams) from two different breeds of hens, Breed X and Breed Y.
| Breed | Mean Weight (g) | Standard Deviation (g) |
|---|---|---|
| Breed X | 58.0 | 2.1 |
| Breed Y | 58.0 | 6.8 |
Using the information in the table, comment on the distribution of egg weights for both breeds.
- Identify the given statistics: Both breeds have the same mean egg weight (58.0 g), but Breed Y has a higher standard deviation (6.8 g) than Breed X (2.1 g).
- Use the required keywords (spread, mean, variability/consistent): Breed X has a smaller standard deviation, meaning the weights deviate less from the mean.
- State the conclusion in context: Breed X produces eggs that are more consistent in weight, while the egg weights of Breed Y have greater spread or variability around the mean.
Answer: Both breeds have the same mean weight (58.0 g), but the egg weights of Breed Y have a greater spread around the mean because of its larger standard deviation (6.8 g>2.1 g). Breed X produces more consistent egg weights.
Quick check
In a cricket series, Batsman P has a mean score of 42 runs with a standard deviation of 6.1. Batsman Q has a mean score of 42 runs with a standard deviation of 18.4. Which batsman is more reliable to score close to 42 runs in the next match? Explain using appropriate statistical terms.
3. Visualising Standard Deviation on Graphs
You can easily spot standard deviation on a histogram or frequency curve:
- Tall, narrow curve/bars: Data values are bunched close to the centre. This represents a small standard deviation.
- Wider, flatter curve/bars: Data values are stretched out over a wide range. This represents a large standard deviation.
For most symmetrical datasets, roughly two-thirds (about 68%) of all values lie within one standard deviation of the mean, and almost all values (about 95%) lie within two standard deviations.
Worked example
Two secondary schools in Trinidad wrote the same Form 5 mock exam. Both schools had an average mark of 55%. School 1 had a standard deviation of 7.5%, while School 2 had a standard deviation of 19.2%. Describe what the histograms of marks for School 1 and School 2 would look like in comparison to each other.
- Compare the standard deviations: School 1 has a low standard deviation (7.5%); School 2 has a high standard deviation (19.2%).
- Relate standard deviation to graph shape: A small standard deviation creates a narrow, tall peak; a large standard deviation creates a wide, spread-out distribution.
- Write the visual description: The histogram for School 1 will be tall and tightly clustered around 55%, whereas the histogram for School 2 will be broader, flatter, and more spread out across low and high scores.
Answer: The histogram for School 1 will be narrow and sharply peaked around the mean (55%), showing little spread. The histogram for School 2 will be wider and flatter, showing that student marks are spread over a much broader range.
Quick check
Two classes have the same mean score on an assignment. Distribution J is tall and narrow, while Distribution K is broad and flat. Which statement is correct?
Common mistakes
- Thinking you need to calculate the standard deviation using complex square-root formulas. CSEC only tests your ability to interpret and compare standard deviations conceptually.
- Confusing the mean with the standard deviation. The mean tells you where the centre of the data lies, while the standard deviation tells you how spread out the data is around that centre.
- Writing vague exam answers like 'Class A did better' instead of using specific keywords such as 'the heights in Class A have a smaller spread around the mean' or 'are more consistent'.
In the exam
- In comparison questions, always quote both the numbers given in the question and the key words: 'mean', 'spread/variation', and 'deviates'.
- Remember that a higher standard deviation does not mean higher marks or better performance; it only means greater inconsistency or spread.
Key terms
- Standard Deviation
- A statistical measure of how widely values in a dataset deviate or spread out from their mean.
- Variability
- The extent to which data points differ from each other and from the mean.
- Consistency
- The degree to which data values stay close to a central value; higher consistency corresponds to a smaller standard deviation.
Practice
Easier to harder. Use paper for your working.
Practice 1
Two machines, M1 and M2, fill 500 mL water bottles in a factory in Barbados. Both machines have a mean fill volume of 500 mL. Machine M1 has a standard deviation of 1.2 mL, and Machine M2 has a standard deviation of 4.8 mL. Which machine is performing better and why?
Practice 2
In an agricultural experiment in Belize, the mean height of tomato plants under Treatment 1 is 65.4 cm with a standard deviation of 4.2 cm. Under Treatment 2, the mean height is 65.4 cm with a standard deviation of 11.8 cm. Comment on the distribution of plant heights under both treatments.
Practice 3
In Form 5, Class A has a mean test score of 70% with a standard deviation of 15%. Class B has a mean test score of 70% with a standard deviation of 5%. In which class is it more likely to find a student who scored above 90%? Justify your answer using standard deviation concepts.
Now try real past-paper questions
1 Paper 2 question on this topic. Quelpr marks your working point by point, like an examiner.
- CSEC Mathematics · 2022 · Paper 2 · Q5 5(b) · 1 markIn Class B, the mean height of the students is 123.5 cm, and the standard deviation 29.87. For Class A, the standard deviation is 21.38. Using the information provided, and your…
Finished the lesson?
0 of 6 checks right on this device.
Read more
- Mathematics for CSEC, pp. 536, 537
- introductory-statistics-2e_-_WEB, pp. 119, 123, 161
- CSEC Maths Study Guide - Maths Crash Course, p. 117
- Collins - Concise Revision Course for CSEC Mathematics, p. 564