A2 2 / A2 3 statistics question — recurring in every A2 2 series · 5 marks
A2 · A2 3 Practical Skills in A2 Biology
The chi-squared test in A-level Biology, worked through
The short answer
Use chi-squared when you have counted categorical data and want to know whether observed numbers differ significantly from expected ones. Calculate χ² = Σ (O − E)² / E, work out degrees of freedom as (number of categories − 1), and compare your value with the critical value at p = 0.05.
The five steps
- State the null hypothesis: there is no significant difference between observed and expected results.
- Work out the expected numbers from the ratio, using the actual total — never a rounded one.
- Tabulate O, E, (O − E), (O − E)² and (O − E)²/E, then sum the last column.
- Degrees of freedom = number of categories − 1 (so 3 for a 9:3:3:1 dihybrid cross).
- Compare with the critical value at p = 0.05 and state whether you accept or reject the null hypothesis.
Worked example
A dihybrid cross gives 160 offspring, expected in a 9:3:3:1 ratio: 90, 30, 30, 10. Observed: 100, 26, 28, 6. The contributions are (100−90)²/90 = 1.11, (26−30)²/30 = 0.53, (28−30)²/30 = 0.13, (6−10)²/10 = 1.60, giving χ² = 3.37.
With 3 degrees of freedom the critical value at p = 0.05 is 7.82. Since 3.37 is less than 7.82, the difference is not significant: we accept the null hypothesis and the results are consistent with a 9:3:3:1 ratio, with any deviation due to chance.
Choosing the right test
| Question | Test |
|---|---|
| Do counts fit an expected ratio or association? | Chi-squared |
| Is there a difference between two means? | t-test |
| Is there a relationship between two variables? | Correlation (Spearman's rank or Pearson's) |
Phrases that earn the marks
- null hypothesis: no significant difference between observed and expected
- χ² = Σ (O − E)² / E
- degrees of freedom = number of categories − 1
- critical value at p = 0.05
- the difference is (not) significant, so we accept/reject the null hypothesis
- any difference is due to chance
Where marks get lost
- Using percentages or means instead of raw counts — chi-squared needs frequencies.
- Calculating degrees of freedom as the number of categories.
- Quoting a value without ever comparing it to the critical value.
- Saying results are 'significant' with no reference to probability.
Try these chi squared test a level biology questions yourself
Write your answer, then see it marked against every mark scheme point before the model answer is revealed.
These questions are written in the style of the CCEA GCE Biology (2016) papers and are not reproduced from any live paper. CCEA owns the copyright in its question papers and mark schemes — always download the official paper and mark scheme from CCEA and use these worked answers alongside them. BioCCEA is an independent study tool and is not endorsed by CCEA.
Exam questions on chi squared test a level biology, marked
Two A2-standard questions in CCEA paper style, each with the full mark scheme, a full-mark answer written the way you should write it, and the point where most candidates drop marks.
A2 2 / A2 3 statistics question — recurring in every A2 2 series · 5 marks
A dihybrid cross gave 152 tall red, 39 tall white, 53 dwarf red and 16 dwarf white offspring (n = 260). Use a chi-squared test to determine whether these results differ significantly from a 9 : 3 : 3 : 1 ratio. The critical value at p = 0.05 with 3 degrees of freedom is 7.82.
Mark scheme — 5 creditworthy points
- Expected values calculated: 146.25, 48.75, 48.75, 16.25
- Correct use of χ² = Σ (O − E)² / E
- χ² = 0.23 + 1.95 + 0.37 + 0.004 = 2.55 (allow 2.5–2.6)
- Degrees of freedom = number of classes − 1 = 3; critical value 7.82
- χ² is less than the critical value, so the difference is not significant at p = 0.05 / the null hypothesis is accepted and the results fit a 9:3:3:1 ratio
Full-mark answer
Expected numbers for 260 offspring in a 9:3:3:1 ratio are 146.25, 48.75, 48.75 and 16.25. Using χ² = Σ (O − E)² / E: (152 − 146.25)²/146.25 = 0.23; (39 − 48.75)²/48.75 = 1.95; (53 − 48.75)²/48.75 = 0.37; (16 − 16.25)²/16.25 = 0.004. χ² = 2.55. Degrees of freedom = 4 − 1 = 3, and the critical value at p = 0.05 is 7.82. Because 2.55 is less than 7.82, the difference between observed and expected results is not significant; any difference is due to chance, so the null hypothesis is accepted and the results do fit a 9:3:3:1 ratio.
Examiner insight: The final marking point requires three things in one sentence: the comparison with the critical value, the words 'not significant', and 'due to chance'. Answers that stop at the χ² value routinely score 3 out of 5.
A2 3 practical skills — choosing a statistical test · 3 marks
State the null hypothesis for a chi-squared test and explain why a chi-squared test, rather than a t-test, is appropriate for genetic cross data.
Command word: Explain — how to answer itMark scheme — 3 creditworthy points
- Null hypothesis: there is no significant difference between the observed and expected results / any difference is due to chance
- Chi-squared is used for categoric (discrete) frequency data / counts of individuals in categories
- A t-test compares the means of two sets of continuous data, which genetic cross data are not
Full-mark answer
The null hypothesis is that there is no significant difference between the observed results and the expected results, and that any difference is due to chance. A chi-squared test is appropriate because genetic cross data are categoric frequency data — counts of individuals falling into discrete phenotype classes. A t-test compares the means of two sets of continuous measurements, so it cannot be applied to counts of phenotypes.
Examiner insight: Say 'frequencies' or 'counts in categories', not 'numbers'. The comparison with the t-test must reference continuous data and means to earn the third mark.
These questions are written in the style of the CCEA GCE Biology (2016) papers and are not reproduced from any live paper. CCEA owns the copyright in its question papers and mark schemes — always download the official paper and mark scheme from CCEA and use these worked answers alongside them. BioCCEA is an independent study tool and is not endorsed by CCEA.
Download the official CCEA paper and mark schemeCommon questions
- What does p = 0.05 mean?
- There is a 5% probability that a difference this large arose by chance. Below that threshold biologists treat the difference as significant.
- When should I not use chi-squared?
- When data are continuous measurements, when you are comparing means, or when expected values are very small (below about 5 in a category).
- How many degrees of freedom for a 9:3:3:1 cross?
- Three — four phenotype categories minus one. The critical value at p = 0.05 is 7.82.
Test yourself on this topic
Generate 10 spec-worded questions on chi squared test a level biology, or photograph your written answer and see it marked line by line against the mark scheme.
Open chi squared test a level biology in the app
These open straight into BioCCEA with the right unit and topic already picked — no setup, no searching.