| Exam Board | Edexcel |
|---|---|
| Module | S2 (Statistics 2) |
| Year | 2019 |
| Session | January |
| Marks | 12 |
| Paper | Download PDF ↗ |
| Mark scheme | Download PDF ↗ |
| Topic | Approximating the Binomial to the Poisson distribution |
| Type | State conditions for Poisson approximation |
| Difficulty | Moderate -0.3 Part (i)(a) is pure recall of standard conditions (n large, p small, np moderate). Part (i)(b) is a routine Poisson approximation calculation. Parts (ii)(a-b) test definitions/understanding at a basic level. Parts (ii)(c-d) require working backwards from a normal probability then applying continuity correction, which is slightly more involved but still follows standard S2 procedures with no novel problem-solving required. |
| Spec | 2.01c Sampling techniques: simple random, opportunity, etc2.04d Normal approximation to binomial5.02l Poisson conditions: for modelling5.02m Poisson: mean = variance = lambda5.05a Sample mean distribution: central limit theorem5.05c Hypothesis test: normal distribution for population mean |
| Answer | Marks | Guidance |
|---|---|---|
| Working | Mark | Guidance |
| \(n\) is large and \(p\) is small | B1 | \(n\) is bigger than 10 and \(p < 0.25\) |
| Answer | Marks | Guidance |
|---|---|---|
| Working | Mark | Guidance |
| \([X \sim \text{B}(3000, 0.0025) \rightarrow]\ Y \sim \text{Po}(7.5)\) | B1 | For writing or using Po(7.5) |
| \(P(Y > 7) = 1 - P(Y \leq 7) = 1 - 0.5246 = 0.47536...\) awrt 0.475 | M1, A1 | M1 for writing or using \(1 - P(Y \leq 7)\) oe |
| Answer | Marks | Guidance |
|---|---|---|
| Working | Mark | Guidance |
| A list/database/register of all employees | B1 | B1 must be all employees |
| Answer | Marks | Guidance |
|---|---|---|
| Working | Mark | Guidance |
| The probability distribution of the number of employees that cycle to work [from all possible samples of 150] | B1 | Allow number of employees that cycle to work and their associated probabilities |
| Answer | Marks | Guidance |
|---|---|---|
| Working | Mark | Guidance |
| \(D \sim \text{N}(60, 36)\); \(P(C \leq \alpha) = P(Z \leq z) = 0.0668\) | B1 | 1st B1 for Normal approximation with mean \(= 60\) and variance \(= 36\) / sd \(= 6\) |
| \(\frac{\alpha - "60"}{" 6"} = -1.5\) or \(\frac{"60" - \alpha}{"6"} = 1.5\) | M1, B1 | M1 for standardising with no continuity correction and equating to \(z\) using their mean and sd (if not stated clearly they must be correct), with \( |
| \(\underline{\alpha = 51}\) | A1cao |
| Answer | Marks | Guidance |
|---|---|---|
| Working | Mark | Guidance |
| \(P(C \leq 51) = P(D \leq 51.5)\); \(P\!\left(Z \leq \frac{"51" - "60" + 0.5}{"6"}\right)\) | M1 | M1 for standardising with use of continuity correction 'their \(51\)' \(+ 0.5\); allow same mean and sd used in part (c) |
| \(= P(Z \leq -1.42) = 1 - 0.9222 = 0.0778/0.0782...\) awrt 0.078 | A1 |
# Question 6:
## Part i(a)
| Working | Mark | Guidance |
|---------|------|----------|
| $n$ is large and $p$ is small | B1 | $n$ is bigger than 10 and $p < 0.25$ |
## Part i(b)
| Working | Mark | Guidance |
|---------|------|----------|
| $[X \sim \text{B}(3000, 0.0025) \rightarrow]\ Y \sim \text{Po}(7.5)$ | B1 | For writing or using Po(7.5) |
| $P(Y > 7) = 1 - P(Y \leq 7) = 1 - 0.5246 = 0.47536...$ awrt **0.475** | M1, A1 | M1 for writing or using $1 - P(Y \leq 7)$ oe |
## Part ii(a)
| Working | Mark | Guidance |
|---------|------|----------|
| A **list/database/register** of **all** employees | B1 | B1 must be **all** employees |
## Part ii(b)
| Working | Mark | Guidance |
|---------|------|----------|
| The **probability** distribution of the **number of employees** that **cycle** to work [from all possible samples of 150] | B1 | Allow **number of employees** that **cycle** to work and their associated **probabilities** |
## Part ii(c)
| Working | Mark | Guidance |
|---------|------|----------|
| $D \sim \text{N}(60, 36)$; $P(C \leq \alpha) = P(Z \leq z) = 0.0668$ | B1 | 1st B1 for Normal approximation with mean $= 60$ and variance $= 36$ / sd $= 6$ |
| $\frac{\alpha - "60"}{" 6"} = -1.5$ or $\frac{"60" - \alpha}{"6"} = 1.5$ | M1, B1 | M1 for standardising with no continuity correction and equating to $z$ using their mean and sd (if not stated clearly they must be correct), with $|z| > 1$; 2nd B1 for $-1.5$ (or 1.5); sign must be compatible with their standardisation; allow if used their 36 instead of 6 |
| $\underline{\alpha = 51}$ | A1cao | |
## Part ii(d)
| Working | Mark | Guidance |
|---------|------|----------|
| $P(C \leq 51) = P(D \leq 51.5)$; $P\!\left(Z \leq \frac{"51" - "60" + 0.5}{"6"}\right)$ | M1 | M1 for standardising with use of continuity correction 'their $51$' $+ 0.5$; allow same mean and sd used in part (c) |
| $= P(Z \leq -1.42) = 1 - 0.9222 = 0.0778/0.0782...$ awrt **0.078** | A1 | |
\begin{enumerate}
\item (i) (a) State the conditions under which the Poisson distribution may be used as an approximation to the binomial distribution.
\end{enumerate}
A factory produces tyres for bicycles and $0.25 \%$ of the tyres produced are defective.
A company orders 3000 tyres from the factory.\\
(b) Find, using a Poisson approximation, the probability that there are more than 7 defective tyres in the company's order.\\
(ii) At the company $40 \%$ of employees are known to cycle to work. A random sample of 150 employees is taken. The random variable $C$ represents the number of employees in the sample who cycle to work.\\
(a) Describe a suitable sampling frame that can be used to take this sample.\\
(b) Explain what you understand by the sampling distribution of $C$
Louis uses a normal approximation to calculate the probability that at most $\alpha$ employees in the sample cycle to work. He forgets to use a continuity correction and obtains the incorrect probability 0.0668
Find, showing all stages of your working,\\
(c) the value of $\alpha$\\
(d) the correct probability.\\
\hfill \mbox{\textit{Edexcel S2 2019 Q6 [12]}}