S5 Biology Chi-square Test in Genetics Practice 4: Error Rework
- 2026-11-20
S5 Biology Chi-square Test in Genetics Practice 4: Error Rework
Target the ten most common slips: signs, degrees of freedom, denominators, direction, critical values and sample size.
Chi-square error rework: ten commonly confused points These items rebuild the errors seen most often: adding (O – E) with its sign so the statistic turns negative, using four degrees of freedom for four classes instead of three, dividing by the observed count, reading a small x2 as a poor fit, mixing up the three critical values, treating not-rejecting as proof, ignoring how sample size inflates the statistic, taking 5% as a law of nature, dropping the smallest class and forgetting to square.
01 Paper details (check answers afterwards)
| Item | Detail |
|---|---|
| Questions | 10 |
| Suggested time | 25 |
| Difficulty mix | Foundation 3 · Intermediate 3 · Challenge 3 · Error redo 1 |
| Chapter | Chapter: S5 Biology: The Chi-square Test in Genetics |
| Level | Error rework, 10 items, about 25 minutes |
02 Questions (10 items)
- FoundationCan a chi-square value be negative? Why?
- FoundationIs the degrees of freedom for four classes 3 or 4, and why?
- FoundationShould the denominator be the observed or the expected count, and what goes wrong if it is swapped?
- IntermediateDoes a very small x2 mean a poor fit? What is the correct reading?
- IntermediateHow does the critical value change as degrees of freedom rise from 1 to 2 and 3?
- IntermediateDoes failing to reject an expected ratio prove that the ratio is correct?
- ChallengeWith the same deviation (72% : 28% observed against 3:1), what are x2 for samples of 200 and 2 000?
- ChallengeIs the 5% significance level a law of nature or a convention, and does exceeding it prove the hypothesis false?
- ChallengeOf 400 offspring, 310 and 90 are observed against 3:1. Find x2 and decide.
- Error redoWhat happens if one class is left out of the chi-square calculation?
03 Answers and one-line notes
| # | Answer | One-line note |
|---|---|---|
| 1 | No. Every term is squared and divided by an expectation, so it is zero or positive. | A common slip is to add (O – E) with its sign, which cancels out and gives a misleading figure near zero. |
| 2 | Three, because the expected numbers are fixed by the total, so the last class cannot vary freely. | Degrees of freedom is classes minus one, so four classes give 3; using 4 looks up the wrong critical value, 9.49 instead of 7.82. |
| 3 | The denominator must be the expected count E, not the observed count O. | Dividing by O shrinks the contribution of large classes, so the total comes out too small and the ratio is wrongly kept. |
| 4 | The opposite: a small x2 means observed counts are close to expected, so the fit is good. | The statistic sums squared gaps, so smaller means closer to expectation; calling small values bad reverses the direction. |
| 5 | It rises: 3.84 for df 1, 5.99 for df 2 and 7.82 for df 3. | More classes allow more random fluctuation, so the threshold for the same significance level goes up. |
| 6 | No. It only says the data are consistent with that ratio, and other ratios may fit too. | Not rejecting a hypothesis is not proof of it, and a small sample can easily hide a real deviation. |
| 7 | x2 = 0.96 for 200 and x2 = 9.6 for 2 000. | For 200 the expectation is 150 and 50 against 144 and 56; for 2 000 it is 1 500 and 500 against 1 440 and 560, so ten times the sample gives ten times the statistic. |
| 8 | It is a chosen convention; exceeding it means the deviation is significant, not that the hypothesis is necessarily false. | The 5% figure is customary and 1% may be used instead, so conclusions depend on the level chosen. |
| 9 | x2 = 1.33, below 3.84, so 3:1 is not rejected. | Expectations are 300 and 100, giving (100/300) + (100/100) = 0.333 + 1 = 1.333. |
| 10 | The statistic is underestimated, so the expected ratio is wrongly kept. | Every class must be counted, including the smallest, and the rare double-recessive class is the one most often dropped. |
04 What to do after marking
- After marking, redo only the wrong items and write down which step went wrong (formula, unit, or misread number).
- Repeat the same item two days later; move to the next paper only when both attempts are correct.
- Parents only need the answer and note columns; there is no need to explain every item.
Download the full ten-item paper as a PDF, answers and notes included.Tutor Registration →
Questions and answers are written originally by the TutorZone team and are not taken from any school, publisher or examination authority paper. Every value is checked by computer.



