| Exam Board | OCR MEI |
|---|---|
| Module | S2 (Statistics 2) |
| Year | 2016 |
| Session | June |
| Marks | 16 |
| Paper | Download PDF ↗ |
| Mark scheme | Download PDF ↗ |
| Topic | Approximating the Binomial to the Poisson distribution |
| Type | State exact binomial distribution |
| Difficulty | Standard +0.3 This is a straightforward application of standard distribution approximations with clear signposting. Part (i) is definitional, (ii) is direct binomial calculation, (iii-iv) apply the standard Poisson approximation with given conditions (n large, p small), and (v) uses normal approximation. All steps follow textbook procedures with no novel problem-solving required, making it slightly easier than average. |
| Spec | 5.02b Expectation and variance: discrete random variables5.02c Linear coding: effects on mean and variance5.02i Poisson distribution: random events model5.02j Poisson formula: P(X=x) = e^(-lambda)*lambda^x/x!5.02k Calculate Poisson probabilities5.04b Linear combinations: of normal distributions5.05a Sample mean distribution: central limit theorem |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Marks | Guidance |
| 'Randomly' means that mutations occur with no (predictable) pattern | E1 | In context. Allow "not predictable" |
| 'Independently' means that the occurrence of one mutation does not affect the probability of another mutation occurring | E1 | Must include 'probability' and context. Allow "chance". If not indicated, assume first comment relates to randomness. |
| [2] |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Marks | Guidance |
| \(P(\text{Exactly one}) = \binom{30}{29} \times 0.85^{29} \times 0.15^1 = {}^{20}C_1 \times 0.012^1 \times 0.988^{19}\) | M1 | For correct structure i.e. \(20p(1-p)^{19}\) |
| \(= 0.1908\) | A1 | Allow 0.191. Allow 0.19 www. |
| [2] |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Marks | Guidance |
| Because the number of mutating genes \(X\) is binomially distributed | E1 | Allow B(500, 0.012) or B\((n,p)\) |
| \(n\) is large and \(p\) is small | E1 | Allow the sample is large & \(np \approx np(1-p)\) or \(np\) not too large. Condone suitable numerical ranges e.g. \(n > 30\), \(p < 0.1\). Do not allow "the number is large and probability is small". Allow "probability of success/a gene mutating is small" for \(p\) is small |
| [2] |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Marks | Guidance |
| \(\lambda = 500 \times 0.012 = 6\) | B1 | For mean |
| \(P(2 \text{ mutations}) = e^{-0.85}\dfrac{0.85^2}{1!}\) \([0.0620 - 0.0174 \text{ from tables}]\) | M1 | Correct structure for \(P(=2)\) using Poisson pdf or tables. |
| \(= 0.0446\) | A1 | CAO Allow 0.04462 or 0.045www |
| [3] |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Marks | Guidance |
| From tables \(P(\text{At least two}) = 1 - P(\leq 1)\) \(= 1 - 0.0174 = 0.9826\) | M1 | For using \(1 - P(\leq 1)\) using their mean. |
| A1 | CAO Allow 0.983. Allow 0.98 www. | |
| [2] |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Marks | Guidance |
| Mean \(50000 \times 0.012 = 600\), Var \(= 50000 \times 0.012 \times 0.988 = 592.8\) | B1 | For Normal approximation (SOI). |
| Using Normal approx. to the binomial, \(X \sim N(600, 592.8)\) | B1 | For correct parameters (SOI). |
| \(P(X \geq 650) = P\!\left(Z \leq \dfrac{30.5 - 25.5}{\sqrt{25.5}}\right)\) | B1 | For 649.5 |
| \(= P(Z > 2.033) = 1 - \Phi(2.033) = 1 - 0.9789\) | M1 | For standardisation and probability calculation using correct tail. |
| \(= 0.0211\) | A1 | CAO (Allow answer from calculator 0.0210) |
| [5] |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Marks | Guidance |
| Mean \(100 \times 6 = 600\), \(X \sim N(600, 600)\) | B1, B1 | For Normal approximation (SOI). For correct parameters (SOI). |
| \(P(X \geq 650) = P\!\left(Z \leq \dfrac{30.5-25.5}{\sqrt{25.5}}\right)\) | B1 | For 649.5 |
| \(= P(Z > 2.021) = 1 - \Phi(2.021) = 1 - 0.9783\) | M1 | For standardisation and probability calculation using correct tail. |
| \(= 0.0217\) | A1 | CAO (Allow answer from calculator 0.0216) |
| [5] |
# Question 2:
## Part (i)
| Answer | Marks | Guidance |
|--------|-------|----------|
| 'Randomly' means that **mutations** occur with no (predictable) pattern | E1 | In context. Allow "not predictable" |
| 'Independently' means that the occurrence of one **mutation** does not affect the **probability** of another mutation occurring | E1 | Must include 'probability' and context. Allow "chance". If not indicated, assume first comment relates to randomness. |
| **[2]** | | |
## Part (ii)
| Answer | Marks | Guidance |
|--------|-------|----------|
| $P(\text{Exactly one}) = \binom{30}{29} \times 0.85^{29} \times 0.15^1 = {}^{20}C_1 \times 0.012^1 \times 0.988^{19}$ | M1 | For correct structure i.e. $20p(1-p)^{19}$ |
| $= 0.1908$ | A1 | Allow 0.191. Allow 0.19 www. |
| **[2]** | | |
## Part (iii)
| Answer | Marks | Guidance |
|--------|-------|----------|
| Because the number of mutating genes $X$ is binomially distributed | E1 | Allow B(500, 0.012) or B$(n,p)$ |
| $n$ is large and $p$ is small | E1 | Allow the sample is large & $np \approx np(1-p)$ or $np$ not too large. Condone suitable numerical ranges e.g. $n > 30$, $p < 0.1$. Do not allow "the number is large and probability is small". Allow "probability of success/a gene mutating is small" for $p$ is small |
| **[2]** | | |
## Part (iv)(A)
| Answer | Marks | Guidance |
|--------|-------|----------|
| $\lambda = 500 \times 0.012 = 6$ | B1 | For mean |
| $P(2 \text{ mutations}) = e^{-0.85}\dfrac{0.85^2}{1!}$ $[0.0620 - 0.0174 \text{ from tables}]$ | M1 | Correct structure for $P(=2)$ using Poisson pdf or tables. |
| $= 0.0446$ | A1 | CAO Allow 0.04462 or 0.045www |
| **[3]** | | |
## Part (iv)(B)
| Answer | Marks | Guidance |
|--------|-------|----------|
| From tables $P(\text{At least two}) = 1 - P(\leq 1)$ $= 1 - 0.0174 = 0.9826$ | M1 | For using $1 - P(\leq 1)$ using their mean. |
| | A1 | CAO Allow 0.983. Allow 0.98 www. |
| **[2]** | | |
## Part (v)
| Answer | Marks | Guidance |
|--------|-------|----------|
| Mean $50000 \times 0.012 = 600$, Var $= 50000 \times 0.012 \times 0.988 = 592.8$ | B1 | For Normal approximation (SOI). |
| Using Normal approx. to the binomial, $X \sim N(600, 592.8)$ | B1 | For correct parameters (SOI). |
| $P(X \geq 650) = P\!\left(Z \leq \dfrac{30.5 - 25.5}{\sqrt{25.5}}\right)$ | B1 | For 649.5 |
| $= P(Z > 2.033) = 1 - \Phi(2.033) = 1 - 0.9789$ | M1 | For standardisation and probability calculation using correct tail. |
| $= 0.0211$ | A1 | CAO (Allow answer from calculator 0.0210) |
| **[5]** | | |
**Alternative solution using Normal approx. to Poisson:**
| Answer | Marks | Guidance |
|--------|-------|----------|
| Mean $100 \times 6 = 600$, $X \sim N(600, 600)$ | B1, B1 | For Normal approximation (SOI). For correct parameters (SOI). |
| $P(X \geq 650) = P\!\left(Z \leq \dfrac{30.5-25.5}{\sqrt{25.5}}\right)$ | B1 | For 649.5 |
| $= P(Z > 2.021) = 1 - \Phi(2.021) = 1 - 0.9783$ | M1 | For standardisation and probability calculation using correct tail. |
| $= 0.0217$ | A1 | CAO (Allow answer from calculator 0.0216) |
| **[5]** | | |
---
2 When a genetic sequence of plant DNA is given a dose of radiation, some of the genes may mutate. The probability that a gene mutates is 0.012 . Mutations occur randomly and independently.
\begin{enumerate}[label=(\roman*)]
\item Explain the meanings of the terms 'randomly' and 'independently' in this context.
A short stretch of DNA containing 20 genes is given a dose of radiation.
\item Find the probability that exactly 1 out of the 20 genes mutates.
A longer stretch of DNA containing 500 genes is given a dose of radiation.
\item Explain why a Poisson distribution is an appropriate approximating distribution for the number of genes that mutate.
\item Use this Poisson distribution to find the probability that there are\\
(A) exactly two genes that mutate,\\
(B) at least two genes that mutate.
A third stretch of DNA containing 50000 genes is given a dose of radiation.
\item Use a suitable approximating distribution to find the probability that there are at least 650 genes that mutate.
\end{enumerate}
\hfill \mbox{\textit{OCR MEI S2 2016 Q2 [16]}}