Edexcel A-Level Further Maths
Hypothesis test for the mean of a Poisson distribution
Total 27 marks
Name
Class
Date
- 1A help desk historically receives calls at a mean rate of per hour, modelled by a Poisson distribution. After a publicity campaign, the manager records calls in a randomly chosen hour and wants to test, at the significance level, whether the mean rate of calls has increased.(a)Which of the following gives the correct hypotheses, where is the mean number of calls per hour?[1 mark]
- A
- B
- C
- D
Show the mark scheme
Mark scheme
Answer: C(b)Under , find the probability of observing or more calls in the hour.[1 mark]- A
- B
- C
- D
Show the mark scheme
Mark scheme
Answer: B(c)Write down the conclusion of the test, in context.[2 marks]Show the mark scheme
Mark scheme
B1: , so reject (the result is significant)
B1: there is sufficient evidence at the level that the mean rate of calls per hour has increased
Do not accept: 'the claim is true' or a conclusion that does not mention the rate of callsTotal for question 1: 4 marks
- 2In a long-running textbook, typing errors occur at a mean rate of per page, modelled by a Poisson distribution. A new editor checks randomly chosen pages and finds errors in total. A test is carried out at the significance level to see whether the mean rate of errors has decreased.(a)Let be the total number of errors on the pages. What is the distribution of under ?[1 mark]
- A
- B
- C
- D
Show the mark scheme
Mark scheme
Answer: D(b)Find the probability of observing or fewer errors under .[1 mark]- A
- B
- C
- D
Show the mark scheme
Mark scheme
Answer: A(c)Find the critical region for this test, and state the actual significance level of the test.[2 marks]Show the mark scheme
Mark scheme
B1: critical region (since but )
B1: actual significance level ()
Accept:
Do not accept:Total for question 2: 4 marks
- 3A factory's machines have historically broken down at a mean rate of per week. During a randomly chosen two-week period there are breakdowns. The manager believes that the weekly rate has changed. Breakdowns are assumed to occur at random, independently and at a constant average rate, and the test is carried out at the significance level.(a)State suitable hypotheses for the test, where is the mean number of breakdowns per week, and the distribution of the number of breakdowns in the two-week period under .[3 marks]
Show the mark scheme
Mark scheme
B1:
B1:
B1: under
Accept: hypotheses in terms of , or and for a two-week period if defined(b)Carry out the test.[4 marks]Show the mark scheme
Mark scheme
M1: for
A1:
M1: compare with (half of ), or with
A1: reject ; sufficient evidence at the level that the mean weekly rate of breakdowns has changed
Accept: the critical region with in itTotal for question 3: 7 marks
- 4A company's mail server receives emails at a mean rate of per minute, modelled by a Poisson distribution. A technician suspects that the rate has changed and decides to count the number of emails received in a -minute period, using a two-tailed test at the significance level with in each tail.(a)(i) State the hypotheses, in terms of the mean rate per minute, and the distribution of under .[6 marks]
(ii) Find the critical region for the test, and state the actual significance level.Show the mark scheme
Mark scheme
B1: (i)
B1: (i) under
M1: (ii) uses cumulative probabilities for both tails with in each tail, e.g. ,
A1: (ii) lower tail
A1: (ii) upper tail (since and )
B1: (ii) actual significance level ()
Accept: for the -minute period, if defined(b)The technician counts emails in a single -minute period.[6 marks]
(i) Complete the test.
(ii) Explain why the Poisson model might not be suitable for the arrival of emails, and how this could affect the conclusion.Show the mark scheme
Mark scheme
M1: (i) is not in the critical region (or )
A1: (i) do not reject
B1: (i) insufficient evidence at the level that the mean rate of emails per minute has changed from
B1: (ii) a named condition: emails are not independent or do not arrive at a constant average rate
B1: (ii) a reason in context, e.g. emails arrive in bursts or the rate is higher at the start of the working day
B1: (ii) effect: counts would vary more than a Poisson model predicts, so extreme counts are more likely and the test could wrongly suggest a change (or its conclusion is unreliable)Total for question 4: 12 marks
End of questions