Edexcel S2 2017 June — Question 1 9 marks

Exam BoardEdexcel
ModuleS2 (Statistics 2)
Year2017
SessionJune
Marks9
PaperDownload PDF ↗
Mark schemeDownload PDF ↗
TopicHypothesis test of binomial distributions
TypeTwo-tailed test critical region
DifficultyModerate -0.3 This is a standard S2 hypothesis testing question requiring routine application of binomial distribution tables to find critical regions and perform a significance test. Part (a) involves looking up cumulative probabilities to establish a two-tailed critical region, while part (b) is a one-tailed test with clearly stated context. Both parts follow textbook procedures with no novel problem-solving required, making it slightly easier than average.
Spec5.02b Expectation and variance: discrete random variables5.02c Linear coding: effects on mean and variance5.05c Hypothesis test: normal distribution for population mean

  1. A potter believes that \(20 \%\) of pots break whilst being fired in a kiln. Pots are fired in batches of 25 .
    1. Let \(X\) denote the number of broken pots in a batch. A batch is selected at random. Using a 10\% significance level, find the critical region for a two tailed test of the potter's belief. You should state the probability in each tail of your critical region.
    The potter aims to reduce the proportion of pots which break in the kiln by increasing the size of the batch fired. He now fires pots in batches of 50 . He then chooses a batch at random and discovers there are 6 pots which broke whilst being fired in the kiln.
  2. Test, at the \(5 \%\) level of significance, whether or not there is evidence that increasing the number of pots in a batch has reduced the percentage of pots that break whilst being fired in the kiln. State your hypotheses clearly.

Question 1:
Part (a)
*Note: Allow any letter instead of \(X\) or \(c\) for this question*
AnswerMarks Guidance
Answer/WorkingMark Guidance
\(X \sim B(25, 0.2)\)M1 Writing or using \(B(25, 0.2)\) or \(B(25, \frac{1}{5})\) [allow \(Po(5)\)]. May be written in full or implied by a correct CR
\(P(X \geq 9) = 0.0468\), \(P(X \leq 1) = 0.0274\)A1 Both awrt 0.0468 and awrt 0.0274 seen
\(X = [0 \leq]\ X \leq 1\)A1 \(X \leq 1\) or \(X < 2\) or \(0 \leq X \leq 1\) or \([0,1]\) or \(0,1\) or equivalent statements. \(X \leq c\) and \(c = 1\)
\(9 \leq X\ [\leq 25]\)A1d Dependent on seeing a probability from \(B(25, 0.2)\) and \(X \geq 9\) or \(X > 8\) or \(9 \leq X \leq 25\) or list \(9,10,...,25\) or \([9,25]\) or equivalent. \(X \geq c\) and \(c = 9\)
NB: Final 2 A marks must be for statements with "\(X\)" only (or list) — not in probability statements.
SC: If a probability from \(B(25, 0.2)\) is seen and they have both CR correct but written as probability statements or CR written as \(1 \geq X \geq 9\), award A1 A0 for final 2 marks. (4)
Part (b)
AnswerMarks Guidance
Answer/WorkingMark Guidance
\(H_0: p = 0.2\), \(H_1: p < 0.2\)B1 Both hypotheses with \(p\) or \(\pi\), clear which is \(H_0\) and which is \(H_1\)
\(P(X \leq 6) = 0.1034\) or \(CR\ X \leq 5\)M1 Writing or using \(B(50, 0.2)\) and writing or using \(P(X \leq 6)\) or \(P(X \geq 7)\) on its own. May be implied by a correct CR
A1awrt 0.103. Allow \(CR\ X \leq 5\) or \(X < 6\). If not using CR, allow awrt 0.897
Insufficient evidence to reject \(H_0\). Accept \(H_0\), not significant. 6 does not lie in the critical region.M1d Dependent on previous M. Correct statement (do not allow contradicting non-contextual statements). ft their Prob/CR compared with \(0.05/6/(0.95\) if using \(0.8979)\). Do not follow through their hypotheses
No evidence that increasing the batch size has reduced the percentage of broken pots (oe) or evidence that there is no change in the percentage of broken pots (oe)A1cso Conclusion must contain words reduced/no change/not affect oe number/percentage/proportion/probability oe, and pots. All previous marks must be awarded for this mark. Do not allow potters claim/belief is wrong/true. NB Correct contextual statement on its own scores M1A1
(5)
(Total 9)
# Question 1:

## Part (a)

*Note: Allow any letter instead of $X$ or $c$ for this question*

| Answer/Working | Mark | Guidance |
|---|---|---|
| $X \sim B(25, 0.2)$ | M1 | Writing or using $B(25, 0.2)$ or $B(25, \frac{1}{5})$ [allow $Po(5)$]. May be written in full or implied by a correct CR |
| $P(X \geq 9) = 0.0468$, $P(X \leq 1) = 0.0274$ | A1 | Both awrt 0.0468 and awrt 0.0274 seen |
| $X = [0 \leq]\ X \leq 1$ | A1 | $X \leq 1$ or $X < 2$ or $0 \leq X \leq 1$ or $[0,1]$ or $0,1$ or equivalent statements. $X \leq c$ and $c = 1$ |
| $9 \leq X\ [\leq 25]$ | A1d | Dependent on seeing a probability from $B(25, 0.2)$ and $X \geq 9$ or $X > 8$ or $9 \leq X \leq 25$ or list $9,10,...,25$ or $[9,25]$ or equivalent. $X \geq c$ and $c = 9$ |

**NB:** Final 2 A marks must be for statements with "$X$" only (or list) — not in probability statements.

**SC:** If a probability from $B(25, 0.2)$ is seen **and** they have both CR correct but written as probability statements **or** CR written as $1 \geq X \geq 9$, award A1 A0 for final 2 marks. **(4)**

---

## Part (b)

| Answer/Working | Mark | Guidance |
|---|---|---|
| $H_0: p = 0.2$, $H_1: p < 0.2$ | B1 | Both hypotheses with $p$ or $\pi$, clear which is $H_0$ and which is $H_1$ |
| $P(X \leq 6) = 0.1034$ or $CR\ X \leq 5$ | M1 | Writing or using $B(50, 0.2)$ and writing or using $P(X \leq 6)$ or $P(X \geq 7)$ on its own. May be implied by a correct CR |
| | A1 | awrt 0.103. Allow $CR\ X \leq 5$ or $X < 6$. If not using CR, allow awrt 0.897 |
| Insufficient evidence to reject $H_0$. Accept $H_0$, not significant. 6 does not lie in the critical region. | M1d | Dependent on previous M. Correct statement (do not allow contradicting non-contextual statements). ft their Prob/CR compared with $0.05/6/(0.95$ if using $0.8979)$. Do not follow through their hypotheses |
| No evidence that increasing the batch size has **reduced** the **percentage** of broken **pots (oe)** or evidence that there is **no change** in the **percentage** of broken **pots (oe)** | A1cso | Conclusion must contain words **reduced/no change/not affect oe number/percentage/proportion/probability oe**, and **pots**. All previous marks must be awarded for this mark. Do **not** allow potters claim/belief is wrong/true. **NB** Correct contextual statement on its own scores M1A1 |

**(5)**

**(Total 9)**
\begin{enumerate}
  \item A potter believes that $20 \%$ of pots break whilst being fired in a kiln. Pots are fired in batches of 25 .\\
(a) Let $X$ denote the number of broken pots in a batch. A batch is selected at random. Using a 10\% significance level, find the critical region for a two tailed test of the potter's belief. You should state the probability in each tail of your critical region.
\end{enumerate}

The potter aims to reduce the proportion of pots which break in the kiln by increasing the size of the batch fired. He now fires pots in batches of 50 . He then chooses a batch at random and discovers there are 6 pots which broke whilst being fired in the kiln.\\
(b) Test, at the $5 \%$ level of significance, whether or not there is evidence that increasing the number of pots in a batch has reduced the percentage of pots that break whilst being fired in the kiln. State your hypotheses clearly.

\hfill \mbox{\textit{Edexcel S2 2017 Q1 [9]}}