| Exam Board | Edexcel |
|---|---|
| Module | Paper 3 (Paper 3) |
| Year | 2018 |
| Session | June |
| Marks | 5 |
| Paper | Download PDF ↗ |
| Mark scheme | Download PDF ↗ |
| Topic | Continuous Uniform Random Variables |
| Type | Compare uniform with other distributions |
| Difficulty | Moderate -0.8 This question requires only basic understanding of discrete uniform distributions (writing down probabilities, calculating P(X<50)), followed by straightforward comparison with data and a simple suggestion. No complex calculations, proofs, or novel insights are needed—it's primarily testing interpretation and model criticism at an elementary level. |
| Spec | 2.04a Discrete probability distributions |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Mark | Guidance |
| Correct set of values for \(c\): \(\{0, 1, 2, 3, 4, 5, 6, 7, 8\}\) | B1 | Allow \(\{\frac{1}{8}, \frac{2}{8}, \ldots, \frac{8}{8}\}\) |
| \(P(C = c) = \frac{1}{9}\) for each value | B1ft | Correct probs consistent with discrete uniform distribution; allow as probability function with \(P(X=x) = \frac{1}{9}\) for \(0 \leq x \leq 8\) provided \(x = \{0,1,2,\ldots,8\}\) clearly defined |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Mark | Guidance |
| \(P(C < 4) = \frac{4}{9}\) (accept 0.444 or better) | B1 | For using correct model to get \(\frac{4}{9}\) (o.e.) |
| SC: If sample space \(\{1,\ldots,8\}\) scored B0B1 in (a), allow \(P(C<4) = \frac{3}{8}\) to score B1 |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Mark | Guidance |
| Probability lower than expected suggests model is not good | B1ft | Comment stating model is or is not good based on their part (a) and probability in (b); \( |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Mark | Guidance |
| e.g. Cloud cover will vary from month to month and place to place, so use a non-uniform distribution | B1 | Sensible refinement considering variations in month or location; just saying "not uniform" is B0; Context & "non-uniform": allow mention of different locations, months and non-uniform, or use more locations to form new distribution with probabilities based on frequencies; Context & "binomial": allow mention of different locations, months and binomial; Just refined model: must be outlined and discrete and non-uniform (e.g. higher probabilities for more cloud cover or lower for less); Continuous model e.g. normal is B0 |
# Question 1:
## Part (a)
| Answer | Mark | Guidance |
|--------|------|----------|
| Correct set of values for $c$: $\{0, 1, 2, 3, 4, 5, 6, 7, 8\}$ | B1 | Allow $\{\frac{1}{8}, \frac{2}{8}, \ldots, \frac{8}{8}\}$ |
| $P(C = c) = \frac{1}{9}$ for each value | B1ft | Correct probs consistent with discrete uniform distribution; allow as probability function with $P(X=x) = \frac{1}{9}$ for $0 \leq x \leq 8$ provided $x = \{0,1,2,\ldots,8\}$ clearly defined |
## Part (b)
| Answer | Mark | Guidance |
|--------|------|----------|
| $P(C < 4) = \frac{4}{9}$ (accept 0.444 or better) | B1 | For using correct model to get $\frac{4}{9}$ (o.e.) |
| **SC:** If sample space $\{1,\ldots,8\}$ scored B0B1 in (a), allow $P(C<4) = \frac{3}{8}$ to score B1 | | |
## Part (c)
| Answer | Mark | Guidance |
|--------|------|----------|
| Probability lower than expected suggests model is **not** good | B1ft | Comment stating model is or is not good based on their part (a) and probability in (b); $|(b) - 0.315| > 0.05$: allow "not suitable", "not accurate" etc; $|(b) - 0.315| \leq 0.05$: allow comment suggesting it is suitable; **No prob in (b):** allow comparison mentioning 50% or 0.5 rejecting model; **No prob in (b) and no 50% or 0.5 or (b) $> 1$:** scores B0; ignore comments about location or weather patterns |
## Part (d)
| Answer | Mark | Guidance |
|--------|------|----------|
| e.g. Cloud cover will vary from month to month and place to place, so use a non-uniform distribution | B1 | Sensible refinement considering variations in month or location; just saying "not uniform" is B0; **Context & "non-uniform":** allow mention of different locations, months **and** non-uniform, or use more locations to form new distribution with probabilities based on frequencies; **Context & "binomial":** allow mention of different locations, months **and** binomial; **Just refined model:** must be outlined and discrete and non-uniform (e.g. higher probabilities for more cloud cover or lower for less); **Continuous model** e.g. normal is B0 |
\begin{enumerate}
\item Helen believes that the random variable $C$, representing cloud cover from the large data set, can be modelled by a discrete uniform distribution.\\
(a) Write down the probability distribution for $C$.\\
(b) Using this model, find the probability that cloud cover is less than 50\%
\end{enumerate}
Helen used all the data from the large data set for Hurn in 2015 and found that the proportion of days with cloud cover of less than $50 \%$ was 0.315\\
(c) Comment on the suitability of Helen's model in the light of this information.\\
(d) Suggest an appropriate refinement to Helen's model.
\hfill \mbox{\textit{Edexcel Paper 3 2018 Q1 [5]}}