OCR H240/02 2018 June — Question 10 9 marks

Exam BoardOCR
ModuleH240/02 (Pure Mathematics and Statistics)
Year2018
SessionJune
Marks9
PaperDownload PDF ↗
TopicType I/II errors and power of test
TypeCarry out hypothesis test
DifficultyStandard +0.3 This is a straightforward hypothesis test question with standard normal distribution. Part (i)-(ii) require simple understanding of random sampling (810 > 784), and part (iii) is a routine one-tailed z-test with given parameters requiring no problem-solving insight—just mechanical application of the test procedure at a specified significance level.
Spec2.01c Sampling techniques: simple random, opportunity, etc2.05d Sample mean as random variable2.05e Hypothesis test for normal mean: known variance

10 A certain forest contains only trees of a particular species. Dipak wished to take a random sample of 5 trees from the forest. He numbered the trees from 1 to 784. Then, using his calculator, he generated the random digits 14781049 . Using these digits, Dipak formed 5 three-digit numbers. He took the first, second and third digits, followed by the second, third and fourth digits and so on. In this way he obtained the following list of numbers for his sample. $$\begin{array} { l l l l l } 147 & 478 & 781 & 104 & 49 \end{array}$$
  1. Explain why Dipak omitted the number 810 from his list.
  2. Explain why Dipak's sample is not random. The mean height of all trees of this species is known to be 4.2 m . Dipak wishes to test whether the mean height of trees in the forest is less than 4.2 m . He now uses a correct method to choose a random sample of 50 trees and finds that their mean height is 4.0 m . It is given that the standard deviation of trees in the forest is 0.8 m .
  3. Carry out the test at the \(2 \%\) significance level.

Question 10 (Hypothesis Testing):
Part (unlabelled - main hypothesis test):
AnswerMarks Guidance
\(H_0: \mu = \frac{35}{6}\)B1 AO 1.1
\(H_1: \mu > \frac{35}{6}\) where \(\mu\) = pop mean no. of 2'sB1 AO 2.5
\(N(\frac{35}{6}, \frac{175}{36})\) or \(N(5.833, 4.861)\) soiM1 AO 3.3
\(P(X \geq 10) = 1 - P(X < 9.5)\) or \(P(X \geq 11) = 1 - P(X < 10.5)\)M1 AO 1.1a
\(P(X \geq 10) = 0.048\)A0 AO 2.1
\(P(X \geq 11) = 0.017\) (0.04 lies between these hence)A1 AO 3.4
Rejection region is \(X \geq 11\); Special case using N~Bin Method BA1 AO 2.2a
Method B:
AnswerMarks Guidance
\(H_0: \mu = \frac{35}{6}\)B1 AO 1.1
\(H_1: \mu > \frac{35}{6}\) where \(\mu\) = pop mean no. of 2'sB1 AO 2.5
\(N(\frac{35}{6}, \frac{175}{36})\) or \(N(5.833, 4.861)\) soiM1 AO 3.3
\(P(X > a) = 0.04\) soiM1 AO 1.1a
\(\frac{35}{6} + 1.751 \times \sqrt{\frac{175}{36}}\)A1 AO 2.1
\(= 9.69\) or \(9.7\)A0 AO 3.4
Rejection region is \(X \geq 11\)A1 AO 2.2a
Part (i):
AnswerMarks Guidance
Only 784 trees and \(810 > 784\)E1 [1] AO 2.4
Part (ii):
AnswerMarks Guidance
e.g. Each no. not independent of previous no. Each no. is related to the nextE1 [1] AO 2.3
Part (iii):
AnswerMarks Guidance
\(H_0: \mu = 4.2\)B1 AO 1.1
\(H_1: \mu < 4.2\) where \(\mu\) is mean height of trees (in the wood)B1 AO 2.5
\(\bar{X} \sim N(4.2, \frac{0.8^2}{50})\) and \(\bar{X} < 4.0\) or \(\bar{X} \leq 4.0\)M1 AO 3.3
\(P(\bar{X} < 4.0) = 0.038549...\) or \(0.039\)A1 AO 3.4
Compare \(0.02\)A1 AO 1.1
Do not reject \(H_0\)M1 AO 2.2b
There is insufficient evidence that mean height of these trees in the wood is less than 4.2m.A1f AO 3.5a
# Question 10 (Hypothesis Testing):

## Part (unlabelled - main hypothesis test):

$H_0: \mu = \frac{35}{6}$ | B1 | AO 1.1 |

$H_1: \mu > \frac{35}{6}$ where $\mu$ = pop mean no. of 2's | B1 | AO 2.5 | **B1B0** one error e.g. undefined $\mu$ or two-tail |

$N(\frac{35}{6}, \frac{175}{36})$ or $N(5.833, 4.861)$ soi | M1 | AO 3.3 | Allow incorrect variance |

$P(X \geq 10) = 1 - P(X < 9.5)$ or $P(X \geq 11) = 1 - P(X < 10.5)$ | M1 | AO 1.1a | $\geq 1$ of these probabilities attempted | $P(X < 9.5)$ or $P(X < 10.5)$ |

$P(X \geq 10) = 0.048$ | A0 | AO 2.1 | BC | $P(X < 9.5) = 0.952$ |

$P(X \geq 11) = 0.017$ (0.04 lies between these hence) | A1 | AO 3.4 | BC | $P(X < 10.5) = 0.983$ (0.96 between these) |

Rejection region is $X \geq 11$; Special case using N~Bin Method B | A1 | AO 2.2a | dep $\geq$ one of above probs seen & correct | rej'n region is $X \geq 11$ |

**Method B:**

$H_0: \mu = \frac{35}{6}$ | B1 | AO 1.1 |

$H_1: \mu > \frac{35}{6}$ where $\mu$ = pop mean no. of 2's | B1 | AO 2.5 | **B1B0** one error e.g. undefined $\mu$ or two-tail |

$N(\frac{35}{6}, \frac{175}{36})$ or $N(5.833, 4.861)$ soi | M1 | AO 3.3 | Allow incorrect variance |

$P(X > a) = 0.04$ soi | M1 | AO 1.1a | $z = \Phi^{-1}(0.96)$ $(= 1.751)$ |

$\frac{35}{6} + 1.751 \times \sqrt{\frac{175}{36}}$ | A1 | AO 2.1 | dep $\Phi^{-1}(0.96)$ attempt. May be implied **BC** |

$= 9.69$ or $9.7$ | A0 | AO 3.4 |

Rejection region is $X \geq 11$ | A1 | AO 2.2a | [7] |

---

## Part (i):

Only 784 trees and $810 > 784$ | E1 [1] | AO 2.4 | or other similar |

## Part (ii):

e.g. Each no. not independent of previous no. Each no. is related to the next | E1 [1] | AO 2.3 | Allow 2nd digit of each no. is 1st of next; Consecutive nos share two digits; or similar correct; Digits are re-used; Ignore all else |

---

## Part (iii):

$H_0: \mu = 4.2$ | B1 | AO 1.1 | Allow other letters except $X$ or $\bar{X}$ |

$H_1: \mu < 4.2$ where $\mu$ is mean height of trees (in the wood) | B1 | AO 2.5 | One error e.g. undefined $\mu$ or 2-tail: B0B1 |

$\bar{X} \sim N(4.2, \frac{0.8^2}{50})$ and $\bar{X} < 4.0$ or $\bar{X} \leq 4.0$ | M1 | AO 3.3 | Stated or implied; Allow $\bar{X} > 4.0$ or $\bar{X} = 4.0$ | $\Phi^{-1}(0.98) = 2.054$; $4.2 - 2.054 \times \frac{0.8}{\sqrt{50}} = 3.968$ |

$P(\bar{X} < 4.0) = 0.038549...$ or $0.039$ | A1 | AO 3.4 | **BC** Allow 0.038; NB 0.038... implies M1A1 | comp their 3.968 with 4.0 |

Compare $0.02$ | A1 | AO 1.1 | dep $P(\bar{X} < 4.0)$ attempted |

Do not reject $H_0$ | M1 | AO 2.2b | Allow Accept $H_0$; dep $P(\bar{X} < 4.0)$ attempted | Can be implied by conclusion |

There is insufficient evidence that mean height of these trees in the wood is less than 4.2m. | A1f | AO 3.5a | In context, not definite; e.g. "Mean height not less than 4.2m": A0 | [7] |

---
10 A certain forest contains only trees of a particular species. Dipak wished to take a random sample of 5 trees from the forest. He numbered the trees from 1 to 784. Then, using his calculator, he generated the random digits 14781049 . Using these digits, Dipak formed 5 three-digit numbers. He took the first, second and third digits, followed by the second, third and fourth digits and so on. In this way he obtained the following list of numbers for his sample.

$$\begin{array} { l l l l l } 
147 & 478 & 781 & 104 & 49
\end{array}$$

(i) Explain why Dipak omitted the number 810 from his list.\\
(ii) Explain why Dipak's sample is not random.

The mean height of all trees of this species is known to be 4.2 m . Dipak wishes to test whether the mean height of trees in the forest is less than 4.2 m . He now uses a correct method to choose a random sample of 50 trees and finds that their mean height is 4.0 m . It is given that the standard deviation of trees in the forest is 0.8 m .\\
(iii) Carry out the test at the $2 \%$ significance level.

\hfill \mbox{\textit{OCR H240/02 2018 Q10 [9]}}