Choose data analysis and statistics
Process results with appropriate tables, graphs, summaries and statistical methods while explaining assumptions and limits.
Cambridge International Biology 9700, 2028–2030. Paper 5 assesses planning, analysis and evaluation. These original practice tasks are not Cambridge exam questions or mark schemes.
Before you begin
- Use biological vocabulary and basic calculations from the AS Biology course. Follow your school laboratory rules and teacher instructions for all practical work.
Work on paper. Try each question before revealing help, and explain why your method works.
Quick readiness check
What should guide the choice of statistical test?
What you will learn
- Calculate suitable means, rates and percentage changes.
- Use spread measures and error bars cautiously.
- Choose a syllabus statistical test that fits the data and question.
Start with data type and question
Identify whether data are categorical, ranked or quantitative, and whether the question asks about a difference or association. These choices guide a suitable table, graph and statistical method.
Calculate means, rates or percentage changes only when they answer the question. Keep raw values visible so the reader can see the evidence behind a summary.
Use uncertainty without overclaiming
Standard deviation describes spread among observations; standard error concerns precision of an estimated mean. Confidence intervals show a range of plausible values under their assumptions. Error bars can help compare means, but their type and meaning must be stated.
Select a statistical test from the syllabus that matches the data and question, check its assumptions, state a null hypothesis and interpret the result in context. Statistical significance does not by itself prove causation or biological importance.
Pause and explain
What does standard deviation mainly describe?
Worked example
Two independent groups produce continuous measurements. What should you check before selecting a test to compare their means?
Show the worked solution
- Confirm the question is a difference between means.
- Check sample design and assumptions required by the syllabus test.
- State the null hypothesis and interpret the test result with the data.
Answer Check that the data and sample design meet the assumptions for the relevant syllabus test, such as a t-test. State a null hypothesis of no difference in population means and interpret the result alongside the size and spread of the measurements.
From guided practice to a new situation
Write your answer and reasoning first. Use a hint only if you are stuck. The model solution is for self-checking; your written work is not automatically marked.
A student compares mean leaf lengths in two groups. What information should be checked before using a t-test?
Give me a hint
Check design and the t-test assumptions stated in the syllabus.
Compare my reasoning
- Confirm measurements are quantitative and groups are appropriately independent for the chosen test.
- Check distribution and other syllabus assumptions.
- State the null hypothesis of no difference in population means.
Check that the quantitative samples and their assumptions are appropriate for the syllabus t-test; state the null hypothesis that the population means do not differ.
Look for these in your work
- Question and data matched
- Assumptions considered
- Null hypothesis stated
A table shows n = 3 repeats with mean ± standard deviation. What can be said about the spread, and what remains uncertain?
Give me a hint
Describe the variation in observed repeats without overstating the population.
Compare my reasoning
- Standard deviation summarises how spread out the three results are.
- A small sample limits confidence about the broader population.
- More repeats could improve the estimate.
The standard deviation describes spread among the three observed repeats, but three measurements provide limited evidence about the full population; more replicates may improve confidence.
Look for these in your work
- Spread correctly interpreted
- Sample limitation stated
Two treatments have overlapping standard-error bars. Can you conclude there is no difference?
Give me a hint
Treat an informal graph comparison cautiously.
Compare my reasoning
- State what the bars represent.
- Do not infer a formal test result from overlap alone.
- Use the suitable statistical test and consider sample size and assumptions.
No. Error-bar overlap alone does not establish the absence of a difference. Identify the bars, then use an appropriate test and interpret the evidence with its assumptions.
Look for these in your work
- Bars identified
- Conclusion appropriately cautious
Common mistakes
- Choosing a test by its name rather than the data type and question.
- Treating standard deviation and standard error as interchangeable.
- Claiming statistical significance proves the biological explanation.
What can you explain now?
What should guide the choice of statistical test?
Compare with the explanation
The data type, question and test assumptions
A suitable test matches the data and comparison.
After trying it yourself, choose your next review. This is your self-assessment.
Your review choice appears on Today. Sign in to sync it across devices.
Make it stick
How do standard deviation and standard error differ, and what does a statistical test add?
If you needed the solution, close it and solve the problem again from a blank page. A correct answer is stronger when you can explain the reason for each step.