Robinson Tuition
AS Further Statistics 1 · Edexcel 8FM0 · free Further Maths worksheet

Chi-squared goodness of fit

Expected frequencies for a discrete uniform, binomial or Poisson model, estimating a parameter from the data, combining classes with expected frequency under 5, degrees of freedom, the test statistic and conclusion.

12 original questions, 97 marks. Type your answers below for an instant mark and a score (algebra in any equivalent form, e.g. 2sqrt(3) or 2√3), or print the worksheet, mark it with the answers sheet, and use the solutions to see every step written out by hand.

Worksheet PDFWorked solutions PDFAnswers PDF

The questions

1

A spinner has five equal sections coloured red, blue, green, yellow and white. Amira spins it 150 times and records the colour each time.

ColourRedBlueGreenYellowWhite
Frequency3624332136

She wants to test whether the spinner is fair.

  1. Write down suitable hypotheses for the test.
  2. Find the expected frequency for each colour if the spinner is fair.
  3. State the number of degrees of freedom and the critical value for a test at the 5% level of significance.
3 marks
Show answer
a) H0: the spinner is fair (discrete uniform model fits), H1: the spinner is not fair b) 30 c) 4 degrees of freedom, critical value 9.488
2

The number of people visiting a village library on each weekday was recorded over a period of several weeks.

DayMondayTuesdayWednesdayThursdayFriday
Visits5238454164

Test, at the 5% level of significance, whether visits to the library are equally likely on each of the five days. State your hypotheses clearly.

6 marks
Show answer
H0: visits are uniformly distributed over the five days, H1: they are not. Expected 48 each, χ² = 8.958 < 9.488 (4 degrees of freedom), so do not reject H0: no evidence that visits are not equally likely on each day.
3

Oliver rolls an ordinary six-sided dice 300 times. The frequencies of the scores 1 to 5 are shown in the table, but the frequency of a 6 has been smudged.

Score123456
Frequency4158476239f
  1. Find the value of f.
  2. Explain why a test of whether the dice is fair has 5 degrees of freedom.
  3. Test, at the 5% level of significance, whether the dice is fair. State your hypotheses and the critical value clearly.
7 marks
Show answer
a) 53 b) 6 classes, 1 constraint (total 300), 6 - 1 = 5 c) χ² = 8.56 < 11.070, do not reject H0: no evidence the dice is biased
4

A quiz has 5 true or false questions. A teacher believes the 96 students in Year 12 simply guessed every answer, so that the number of correct answers, X, for a student can be modelled by B(5, 0.5). The results were:

Number correct012345
Number of students172635216
  1. Find the expected frequencies under the teacher's model.
  2. Test, at the 5% level of significance, whether B(5, 0.5) is a suitable model for X. State your hypotheses and the critical value clearly.
9 marks
Show answer
a) 3, 15, 30, 30, 15, 3 b) χ² = 11.422 > 7.815, reject H0: B(5, 0.5) is not a suitable model
5

A farm shop sells eggs in boxes of 6. Priya checks 100 boxes and records the number of cracked eggs in each box.

Number of cracked eggs0123456
Number of boxes3837185200

She wants to test whether a binomial distribution is a suitable model for the number of cracked eggs in a box.

  1. Show that a suitable estimate for the probability that an egg is cracked is 0.16
  2. Using this estimate, test at the 5% level of significance whether a binomial distribution is a suitable model. State your hypotheses and the critical value clearly.
9 marks
Show answer
a) mean 0.96, p = 0.96 ÷ 6 = 0.16 b) χ² = 0.895 < 5.991, do not reject H0: binomial model suitable
6

A council helpline manager claims that the number of calls arriving in a minute can be modelled by a Poisson distribution with mean 2. The number of calls in each of 120 randomly chosen minutes is recorded.

Number of calls012345 or more
Number of minutes14303322129

Test, at the 5% level of significance, whether the manager's claim is supported by the data. State your hypotheses and the critical value clearly.

8 marks
Show answer
H0: Po(2) is a suitable model, H1: it is not. Expected frequencies 16.24, 32.48, 32.48, 21.65, 10.83, 6.32; χ² = 1.778 < 11.070 (5 df), so do not reject H0: the claim is supported.
7

Kiran is studying daisies on a school field. She places a 1 m by 1 m square frame at 80 random positions and counts the daisies inside it each time.

Number of daisies0123456
Frequency61522181153
  1. Show that the mean number of daisies per square is 2.5
  2. Test, at the 5% level of significance, whether a Poisson distribution is a suitable model for the number of daisies in a square. State your hypotheses and the critical value clearly.
  3. Give one reason, in context, why a Poisson model might be expected to fit.
10 marks
Show answer
a) 200 ÷ 80 = 2.5 b) χ² = 0.391 < 9.488, do not reject H0: Poisson model suitable c) daisies occur singly, randomly and independently at a constant average rate per square metre
8

An editor counts the typing errors on each of 200 pages of a draft novel. The mean number of errors per page is 1.5 and she uses Po(1.5) to model the number of errors on a page. Her results and some of her expected frequencies are shown below.

Number of errors01234 or more
Observed4870462412
Expectedr66.94s25.1013.13
  1. Find the value of r and the value of s, giving your answers to 2 decimal places.
  2. Explain why the test has 3 degrees of freedom.
  3. The test statistic is 0.89. Test, at the 5% level of significance, whether Po(1.5) is a suitable model. State your hypotheses and the critical value clearly.
7 marks
Show answer
a) r = 44.63, s = 50.20 b) 5 classes - 2 constraints (total, λ estimated) = 3 c) 0.89 < 7.815, do not reject H0: Po(1.5) is suitable
9

A garden centre sows 10 seeds in each of 150 trays and counts how many seeds germinate in each tray.

Seeds germinating345678910
Number of trays21020243032266

No tray had fewer than 3 seeds germinate. The manager wants to test whether B(10, p) is a suitable model.

  1. Show that the estimate of p from these data is 0.7

Using p = 0.7 the manager finds these expected frequencies.

Seeds germinating4 or fewer5678910
Expected7.1015.4430.0240.0235.0218.164.24
  1. Explain why the classes 9 and 10 must be combined, and state the number of degrees of freedom for the test.
  2. The test statistic is 12.82. Test, at the 1% level of significance, whether B(10, p) is a suitable model. State your hypotheses and the critical value.
  3. State, with a reason, whether your conclusion would change at the 5% level.
8 marks
Show answer
a) Σfx = 1050, mean = 7, p = 0.7 b) E(10) = 4.24 < 5; ν = 4 c) 12.82 < 13.277, do not reject H0: B(10, p) suitable d) yes, 12.82 > 9.488 so reject H0 at 5%
10

At a school fair, each of 200 visitors throws 4 hoops at a peg. The number of hoops that land on the peg is recorded for each visitor.

Hoops on the peg01234
Number of visitors1852704614

The stall holder, Megan, says the probability that a hoop lands on the peg is 0.4 and that the throws are independent.

  1. Test, at the 5% level of significance, whether B(4, 0.4) is a suitable model for the number of hoops on the peg. State your hypotheses and the critical value clearly.
  2. Use the data to estimate the probability that a hoop lands on the peg.
  3. Using this estimate, the test statistic for a binomial model is 2.21. Stating the degrees of freedom and the critical value, test at the 5% level whether a binomial model with this estimate is suitable.
  4. Comment on Megan's claim in the light of both tests.
10 marks
Show answer
a) χ² = 29.673 > 9.488, reject H0 b) 0.4825 c) ν = 3, 2.21 < 7.815, do not reject H0 d) binomial shape fits (independent, constant p) but p is about 0.48, not 0.4
11

The numbers of goals scored in the 380 matches of a football league season are shown below.

Goals in a match01234567
Number of matches307298785226204
  1. Show that the mean number of goals per match is 2.6
  2. Test, at the 5% level of significance, whether a Poisson distribution is a suitable model for the number of goals in a match. State your hypotheses and the critical value clearly.
  3. Use your model to estimate the number of matches in the season with more than 4 goals, and compare this with the data.
10 marks
Show answer
a) 988 ÷ 380 = 2.6 b) χ² = 6.783 < 12.592, do not reject H0 c) 46.6 matches (about 47), observed 50: close
12

The heights of 300 Year 7 pupils were measured by different members of staff and recorded to the nearest millimetre. The last digit of each recorded height was noted.

Last digit0123456789
Frequency58192422214923253128
  1. Test, at the 1% level of significance, whether the last digit is equally likely to be any of 0 to 9. State your hypotheses, the degrees of freedom and the critical value clearly.
  2. Identify which digits contribute most to the test statistic and suggest a reason in context.
  3. The 107 heights ending in 0 or 5 are removed. Test, at the 5% level of significance, whether the remaining digits are equally likely.
10 marks
Show answer
a) χ² = 50.867 > 21.666, reject H0 b) 0 and 5: heights rounded to the nearest 5 mm (or 0.5 cm) c) χ² = 4.347 < 14.067, do not reject H0

Your score

Answer the questions above and your score appears here.

Every question here is original and written by Robinson Tuition. It follows the Edexcel AS Further Mathematics specification and suits AQA and OCR Further Maths too; this is not an exam-board paper.

All AS Further Statistics 1 topics