| Exam Board | OCR |
|---|---|
| Module | S4 (Statistics 4) |
| Year | 2007 |
| Session | June |
| Marks | 7 |
| Paper | Download PDF ↗ |
| Mark scheme | Download PDF ↗ |
| Topic | Wilcoxon tests |
| Type | Wilcoxon rank-sum test (Mann-Whitney U test) |
| Difficulty | Standard +0.3 This is a straightforward application of the Wilcoxon rank-sum test with small sample sizes (n₁=4, n₂=5). Students must rank the combined data, calculate the test statistic, and compare to critical values from tables. While it requires understanding of the test procedure, it's a standard textbook exercise with no conceptual complications—slightly easier than average since the ranking is simple and the test is clearly specified. |
| Spec | 5.07b Sign test: and Wilcoxon signed-rank |
| Smokers | 77 | 85 | 90 | 98 | |
| Non-smokers | 59 | 64 | 68 | 80 | 88 |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Mark | Guidance |
| \(4p-(1-p) = 5p-1\) | M1 | For \(4p-1(1-p)\) or equivalent, seen or implied |
| \(5p-1\) or \(-1+5p\) | A1 | cao |
| \(-2p+5(1-p) = 5-7p\) | B1 | For any form of this expression cao |
| \(4(1-p) = 4-4p\) | B1 | For any form of this expression cao [4] |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Mark | Guidance |
| Graph with horizontal axis from 0 to 1 | M1 | For correct structure to graph with a horizontal axis that extends from 0 to 1, but not more than this, and with consistent scales |
| Line \(E=5p-1\) plotted from \((0,-1)\) to \((1,4)\) | A1 ft | For line \(E=5p-1\) plotted from \((0,-1)\) to \((1,4)\) |
| Line \(E=5-7p\) plotted from \((0,5)\) to \((1,-2)\) | A1 ft | For line \(E=5-7p\) plotted from \((0,5)\) to \((1,-2)\) |
| Line \(E=4-4p\) plotted from \((0,4)\) to \((1,0)\) | A1 ft | For line \(E=4-4p\) plotted from \((0,4)\) to \((1,0)\) |
| All three cases correct or ft from (i) | [4] | |
| \(p=0.5\) | B1 | For this or ft their graph [1] |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Mark | Guidance |
| \(5(0.5)-1\) | M1 | For substituting their \(p\) into any of their equations (must be seen, cannot be implied from value) |
| \(= 1.5\) points per game | A1 | For 1.5 cao |
| Bea may not play her best strategy | B1 | For this or equivalent; describing a mixed strategy that involves \(Z\) [3] |
| Answer | Marks | Guidance |
|---|---|---|
| Answer | Mark | Guidance |
| Value \(= 1.5\) | B1 ft | Accept \(-1.5\), ft from (iii) |
| If Amy plays using her optimal strategy, Bea should never play strategy \(Z\) | M1 | For identifying that she should not play \(Z\) |
| Assuming Bea knows Amy will make random choice between \(P\) and \(Q\) so each has probability 0.5, it does not matter how she chooses between \(X\) and \(Y\) | A1 | For a full description of how she should play. (If candidate assumes Bea does not know then Bea should play \(P\) with probability \(\frac{7}{12}\) and \(Q\) with probability \(\frac{5}{12}\)) [3] |
# Question 2 (Paper 4737):
## Part (i):
| Answer | Mark | Guidance |
|--------|------|----------|
| $4p-(1-p) = 5p-1$ | M1 | For $4p-1(1-p)$ or equivalent, seen or implied |
| $5p-1$ or $-1+5p$ | A1 | cao |
| $-2p+5(1-p) = 5-7p$ | B1 | For any form of this expression cao |
| $4(1-p) = 4-4p$ | B1 | For any form of this expression cao **[4]** |
## Part (ii):
| Answer | Mark | Guidance |
|--------|------|----------|
| Graph with horizontal axis from 0 to 1 | M1 | For correct structure to graph with a horizontal axis that extends from 0 to 1, but not more than this, and with consistent scales |
| Line $E=5p-1$ plotted from $(0,-1)$ to $(1,4)$ | A1 ft | For line $E=5p-1$ plotted from $(0,-1)$ to $(1,4)$ |
| Line $E=5-7p$ plotted from $(0,5)$ to $(1,-2)$ | A1 ft | For line $E=5-7p$ plotted from $(0,5)$ to $(1,-2)$ |
| Line $E=4-4p$ plotted from $(0,4)$ to $(1,0)$ | A1 ft | For line $E=4-4p$ plotted from $(0,4)$ to $(1,0)$ |
| All three cases correct or ft from (i) | | **[4]** |
| $p=0.5$ | B1 | For this or ft their graph **[1]** |
## Part (iii):
| Answer | Mark | Guidance |
|--------|------|----------|
| $5(0.5)-1$ | M1 | For substituting their $p$ into any of their equations (must be seen, cannot be implied from value) |
| $= 1.5$ points per game | A1 | For 1.5 cao |
| Bea may not play her best strategy | B1 | For this or equivalent; describing a mixed strategy that involves $Z$ **[3]** |
## Part (iv):
| Answer | Mark | Guidance |
|--------|------|----------|
| Value $= 1.5$ | B1 ft | Accept $-1.5$, ft from (iii) |
| If Amy plays using her optimal strategy, Bea should never play strategy $Z$ | M1 | For identifying that she should not play $Z$ |
| Assuming Bea knows Amy will make random choice between $P$ and $Q$ so each has probability 0.5, it does not matter how she chooses between $X$ and $Y$ | A1 | For a full description of how she should play. (If candidate assumes Bea does not know then Bea should play $P$ with probability $\frac{7}{12}$ and $Q$ with probability $\frac{5}{12}$) **[3]** |
2 Of 9 randomly chosen students attending a lecture, 4 were found to be smokers and 5 were nonsmokers. During the lecture their pulse-rates were measured, with the following results in beats per minute.
\begin{center}
\begin{tabular}{ l l l l l l }
Smokers & 77 & 85 & 90 & 98 & \\
Non-smokers & 59 & 64 & 68 & 80 & 88 \\
\end{tabular}
\end{center}
It may be assumed that these two groups of students were random samples from the student populations of smokers and non-smokers. Using a suitable Wilcoxon test at the $10 \%$ significance level, test whether there is a difference in the median pulse-rates of the two populations.
\hfill \mbox{\textit{OCR S4 2007 Q2 [7]}}