CAIE FP2 2018 June — Question 10 12 marks

Exam BoardCAIE
ModuleFP2 (Further Pure Mathematics 2)
Year2018
SessionJune
Marks12
PaperDownload PDF ↗
Mark schemeDownload PDF ↗
TopicT-tests (unknown variance)
TypePaired sample t-test
DifficultyStandard +0.3 This is a standard paired t-test with straightforward hypotheses (H₀: μ_d ≤ 1 vs H₁: μ_d > 1) and a routine confidence interval calculation. The data is provided in a table requiring simple arithmetic for differences, then application of standard formulas. While it involves multiple parts and careful calculation, it requires no novel insight—just methodical application of A-level statistics procedures with small sample size (n=9).
Spec5.05c Hypothesis test: normal distribution for population mean

10 During the summer months, all members of a large swimming club take part in intensive training. The times taken to swim 50 metres at the beginning of the summer and at the end of the summer are recorded for each member of the club. The time taken, in seconds, at the beginning of the summer is denoted by \(x\) and the time taken at the end of the summer is denoted by \(y\). For a random sample of 9 members the results are shown in the following table.
Member\(A\)\(B\)\(C\)\(D\)\(E\)\(F\)\(G\)\(H\)\(I\)
\(x\)38.540.232.335.136.241.432.038.238.2
\(y\)37.438.131.634.734.238.631.836.336.8
The swimming coach believes that, on average, the time taken by a swimmer to swim 50 metres will decrease by more than one second as a result of the intensive training.
  1. Stating suitable hypotheses and assuming a normal distribution, test the coach's belief at the \(10 \%\) significance level.
  2. Find a 95\% confidence interval for the population mean time taken to swim 50 metres after the intensive training, assuming a normal distribution.

Question 10:
Part 10(i):
AnswerMarks Guidance
\(H_0: \mu_x - \mu_y = 1\), \(H_1: \mu_x - \mu_y > 1\)B1 State both hypotheses (B0 for \(\bar{x}\)...)
\(d_i\): \(1.1\ 2.1\ 0.7\ 0.4\ 2.0\ 2.8\ 0.2\ 1.9\ 1.4\)M1 Consider differences \(d_i\), e.g. \(x_i - y_i\)
\(\bar{d} = 12.6/9 = 1.4\)B1 Find sample mean
\(s^2 = (23.72 - 12.6^2/9)/8\ [= 0.76\) or \(0.8718^2]\)M1 Estimate population variance (allow biased: \([0.6756\) or \(0.8219^2]\))
\(t_{8,\ 0.9} = 1.397\) or \(1.40\)B1 State or use correct tabular \(t\)-value
\(t = (\bar{d} - 1)/(s/\sqrt{9}) = 1.38\) [Accept \(H_0\):] No evidence for coach's beliefM1 A1 Find \(t\) (or compare \(\bar{d} - 1 = 0.4\) with \(t_{8,0.9}\ s/\sqrt{9} = 0.406\)); Consistent conclusion
or time will not decrease by more than 1s\(B1\sqrt{}\)
Total: 8 marks
Part 10(ii):
AnswerMarks Guidance
\(s_y^2 = (11395.79 - 319.5^2/9)/8 = 6.693\) or \(2.587^2\)B1 Estimate population variance using \(y\)'s sample
\(319.5/9 \pm t\sqrt{(s_y^2/9)}\)M1 Find confidence interval (M0 if \(s^2\) not \(s_y^2\))
\(t_{8,\ 0.975} = 2.306\) or \(2.31\)A1 State or use correct tabular value of \(t\)
\(35.5 \pm 1.99\) or \([33.5,\ 37.5]\) (allow \(35.5 \pm 2.0\))A1 Evaluate C.I.; SC B1 (max 1/4) for \(1.4 \pm 0.67\) or \([0.73,\ 2.07]\)
Total: 4 marks
Question 11A:
Part 11A(i):
AnswerMarks Guidance
\(I_{lamina} = \frac{1}{3}kM((\frac{1}{2}a)^2 + (\frac{1}{2}a)^2)\ [= (k/6)Ma^2]\)B1 Find or state MI of lamina about axis at its centre
\(I'_{lamina} = I_{lamina} + kM((3a/2)^2 + (3a/2)^2)\ [= (14k/3)Ma^2]\)M1 A1 Find MI of lamina about axis at \(A\)
\(I_{AB} = \frac{1}{3}Ma^2 + Ma^2\ [= (4/3)Ma^2]\)B1 Find or state MI of \(AB\) (or \(AD\)) about axis at \(A\)
\(I_{BC} = \frac{1}{3}Ma^2 + M(a^2 + (2a)^2)\ [= (16/3)Ma^2]\)M1 A1 Find or state MI of \(BC\) (or \(DC\)) about axis at \(A\)
OR: \(I_{rod} = \frac{1}{3}Ma^2 + Ma^2\ [= (4/3)Ma^2]\)(B1) Find or state MI of any rod about axis at centre of frame
\(I_{frame} = 4 \times I_{rod} + 4M(a^2 + a^2)\ [= (40/3)Ma^2]\)(M1 A1) Find or state MI of frame about axis at \(A\)
\(I = (14k/3 + 2 \times 4/3 + 2 \times 16/3)Ma^2\) or \((14k/3 + 40/3)Ma^2\)M1 Verify MI of system about axis at \(A\)
\(= \frac{2}{3}Ma^2(7k + 20)\)A1 AG A0 if inadequate explanation
Total: 8 marks
Part 11A(ii):
AnswerMarks Guidance
\(\frac{1}{2}I\omega^2 = kMg \times 3a + 2Mg \times 2a + Mg \times 4a\) or \(kMg \times 3a + 4Mg \times 2a\)M1 A2 Find \(\omega^2\) or angular speed \(\omega\) when \(D\) below \(B\) by energy; Award A1 if error in only term
\(\omega^2 = \{3(3k+8)/(7k+20)\}\ g/a\); \(4 \times 3(3k+8) = 5(7k+20)\), \(k=4\)A1 Find \(k\) by equating \(\omega^2\) to \(\{\frac{1}{2}\sqrt{(5g/a)}\}^2\)
M1 A1
Total: 6 marks
Question 11B:
Part 11B(i):
AnswerMarks Guidance
\(\bar{x} = 469/250 = 1.876\) and \(\sigma^2 = (1195 - 469^2/250)/249 = 1.266\)B1 AG / B1 AG Verify mean and unbiased variance of data, showing method
\(6 \times 0.313 = 1.878\) and \(6 \times 0.313 \times 0.687 = 1.29[0]\)M1 A1 Find mean \(np\) and variance \(npq\) of binomial distribution
Means and variances are similar for \(X\) and \(B(6,\ 0.313)\)A1 Valid explanation (AEF; needs \(1.878\), \(1.290\) correct to \(0.002\))
Total: 4 marks
Part 11B(ii):
AnswerMarks Guidance
\(250 \times\ ^6C_4 \times 0.313^4 \times 0.687^2\ [= 250 \times 0.06795 = 16.99]\); Allow \(49.7 \times (^6C_4 \times 0.313)/(^6C_3 \times 0.687)\)M1 A1 Show how expected frequency for \(x = 4\) is found (AEF for \(^6C_4 = 15\))
Total: 2 marks
Part 11B(iii):
AnswerMarks Guidance
\(H_0\): [Binomial] distribution fits dataB1 State (at least) null hypothesis
\(O_i\): \(22\ 83\ 72\ 53\ \underline{20}\); \(E_i\): \(26.3\ 71.9\ 81.8\ 49.7\ \underline{20.3}\)*M1 A1 Combine last 3 cells so that all exp. value \(\geq 5\)
\(X^2 = 0.703 + 1.714 + 1.174 + 0.219 + 0.004 = 3.81\)M1 A1 Find value of \(\chi^2\) from \(\Sigma(E_i - O_i)^2/E_i\)
No. \(n\) of cells: \(7\ 6\ \underline{5}\); \(\chi^2_{n-2,\ 0.95}\): \(11.07\ 9.488\ \underline{7.815}\)\(B1\sqrt{}\) State or use consistent tabular value \(\chi^2_{n-2,\ 0.95}\) (to 3 s.f.)
Accept \(H_0\) if \(X^2 <\) tabular valueM1 State or imply valid method for conclusion
\(3.81\ [\pm 0.01] < 7.815\) so distribution fits or scientist's belief is correctA1 Conclusion (AEF; requires both values approx. correct)
Total: 8 marks
## Question 10:

### Part 10(i):
| $H_0: \mu_x - \mu_y = 1$, $H_1: \mu_x - \mu_y > 1$ | B1 | State both hypotheses (B0 for $\bar{x}$...) |
| $d_i$: $1.1\ 2.1\ 0.7\ 0.4\ 2.0\ 2.8\ 0.2\ 1.9\ 1.4$ | M1 | Consider differences $d_i$, e.g. $x_i - y_i$ |
| $\bar{d} = 12.6/9 = 1.4$ | B1 | Find sample mean |
| $s^2 = (23.72 - 12.6^2/9)/8\ [= 0.76$ or $0.8718^2]$ | M1 | Estimate population variance (allow biased: $[0.6756$ or $0.8219^2]$) |
| $t_{8,\ 0.9} = 1.397$ or $1.40$ | B1 | State or use correct tabular $t$-value |
| $t = (\bar{d} - 1)/(s/\sqrt{9}) = 1.38$ [Accept $H_0$:] No evidence for coach's belief | M1 A1 | Find $t$ (or compare $\bar{d} - 1 = 0.4$ with $t_{8,0.9}\ s/\sqrt{9} = 0.406$); Consistent conclusion |
| or time will not decrease by more than 1s | $B1\sqrt{}$ | |

**Total: 8 marks**

### Part 10(ii):
| $s_y^2 = (11395.79 - 319.5^2/9)/8 = 6.693$ or $2.587^2$ | B1 | Estimate population variance using $y$'s sample |
| $319.5/9 \pm t\sqrt{(s_y^2/9)}$ | M1 | Find confidence interval (M0 if $s^2$ not $s_y^2$) |
| $t_{8,\ 0.975} = 2.306$ or $2.31$ | A1 | State or use correct tabular value of $t$ |
| $35.5 \pm 1.99$ or $[33.5,\ 37.5]$ (allow $35.5 \pm 2.0$) | A1 | Evaluate C.I.; SC B1 (max 1/4) for $1.4 \pm 0.67$ or $[0.73,\ 2.07]$ |

**Total: 4 marks**

---

## Question 11A:

### Part 11A(i):
| $I_{lamina} = \frac{1}{3}kM((\frac{1}{2}a)^2 + (\frac{1}{2}a)^2)\ [= (k/6)Ma^2]$ | B1 | Find or state MI of lamina about axis at its centre |
| $I'_{lamina} = I_{lamina} + kM((3a/2)^2 + (3a/2)^2)\ [= (14k/3)Ma^2]$ | M1 A1 | Find MI of lamina about axis at $A$ |
| $I_{AB} = \frac{1}{3}Ma^2 + Ma^2\ [= (4/3)Ma^2]$ | B1 | Find or state MI of $AB$ (or $AD$) about axis at $A$ |
| $I_{BC} = \frac{1}{3}Ma^2 + M(a^2 + (2a)^2)\ [= (16/3)Ma^2]$ | M1 A1 | Find or state MI of $BC$ (or $DC$) about axis at $A$ |
| OR: $I_{rod} = \frac{1}{3}Ma^2 + Ma^2\ [= (4/3)Ma^2]$ | (B1) | Find or state MI of any rod about axis at centre of frame |
| $I_{frame} = 4 \times I_{rod} + 4M(a^2 + a^2)\ [= (40/3)Ma^2]$ | (M1 A1) | Find or state MI of frame about axis at $A$ |
| $I = (14k/3 + 2 \times 4/3 + 2 \times 16/3)Ma^2$ or $(14k/3 + 40/3)Ma^2$ | M1 | Verify MI of system about axis at $A$ |
| $= \frac{2}{3}Ma^2(7k + 20)$ | A1 AG | A0 if inadequate explanation |

**Total: 8 marks**

### Part 11A(ii):
| $\frac{1}{2}I\omega^2 = kMg \times 3a + 2Mg \times 2a + Mg \times 4a$ or $kMg \times 3a + 4Mg \times 2a$ | M1 A2 | Find $\omega^2$ or angular speed $\omega$ when $D$ below $B$ by energy; Award A1 if error in only term |
| $\omega^2 = \{3(3k+8)/(7k+20)\}\ g/a$; $4 \times 3(3k+8) = 5(7k+20)$, $k=4$ | A1 | Find $k$ by equating $\omega^2$ to $\{\frac{1}{2}\sqrt{(5g/a)}\}^2$ |
| | M1 A1 | |

**Total: 6 marks**

---

## Question 11B:

### Part 11B(i):
| $\bar{x} = 469/250 = 1.876$ and $\sigma^2 = (1195 - 469^2/250)/249 = 1.266$ | B1 AG / B1 AG | Verify mean and unbiased variance of data, showing method |
| $6 \times 0.313 = 1.878$ and $6 \times 0.313 \times 0.687 = 1.29[0]$ | M1 A1 | Find mean $np$ and variance $npq$ of binomial distribution |
| Means and variances are similar for $X$ and $B(6,\ 0.313)$ | A1 | Valid explanation (AEF; needs $1.878$, $1.290$ correct to $0.002$) |

**Total: 4 marks**

### Part 11B(ii):
| $250 \times\ ^6C_4 \times 0.313^4 \times 0.687^2\ [= 250 \times 0.06795 = 16.99]$; Allow $49.7 \times (^6C_4 \times 0.313)/(^6C_3 \times 0.687)$ | M1 A1 | Show how expected frequency for $x = 4$ is found (AEF for $^6C_4 = 15$) |

**Total: 2 marks**

### Part 11B(iii):
| $H_0$: [Binomial] distribution fits data | B1 | State (at least) null hypothesis |
| $O_i$: $22\ 83\ 72\ 53\ \underline{20}$; $E_i$: $26.3\ 71.9\ 81.8\ 49.7\ \underline{20.3}$ | *M1 A1 | Combine last 3 cells so that all exp. value $\geq 5$ |
| $X^2 = 0.703 + 1.714 + 1.174 + 0.219 + 0.004 = 3.81$ | M1 A1 | Find value of $\chi^2$ from $\Sigma(E_i - O_i)^2/E_i$ |
| No. $n$ of cells: $7\ 6\ \underline{5}$; $\chi^2_{n-2,\ 0.95}$: $11.07\ 9.488\ \underline{7.815}$ | $B1\sqrt{}$ | State or use consistent tabular value $\chi^2_{n-2,\ 0.95}$ (to 3 s.f.) |
| Accept $H_0$ if $X^2 <$ tabular value | M1 | State or imply valid method for conclusion |
| $3.81\ [\pm 0.01] < 7.815$ so distribution fits or scientist's belief is correct | A1 | Conclusion (AEF; requires both values approx. correct) |

**Total: 8 marks**
10 During the summer months, all members of a large swimming club take part in intensive training. The times taken to swim 50 metres at the beginning of the summer and at the end of the summer are recorded for each member of the club. The time taken, in seconds, at the beginning of the summer is denoted by $x$ and the time taken at the end of the summer is denoted by $y$. For a random sample of 9 members the results are shown in the following table.

\begin{center}
\begin{tabular}{ | c | c | c | c | c | c | c | c | c | c | }
\hline
Member & $A$ & $B$ & $C$ & $D$ & $E$ & $F$ & $G$ & $H$ & $I$ \\
\hline
$x$ & 38.5 & 40.2 & 32.3 & 35.1 & 36.2 & 41.4 & 32.0 & 38.2 & 38.2 \\
\hline
$y$ & 37.4 & 38.1 & 31.6 & 34.7 & 34.2 & 38.6 & 31.8 & 36.3 & 36.8 \\
\hline
\end{tabular}
\end{center}

The swimming coach believes that, on average, the time taken by a swimmer to swim 50 metres will decrease by more than one second as a result of the intensive training.\\
(i) Stating suitable hypotheses and assuming a normal distribution, test the coach's belief at the $10 \%$ significance level.\\

(ii) Find a 95\% confidence interval for the population mean time taken to swim 50 metres after the intensive training, assuming a normal distribution.\\

\hfill \mbox{\textit{CAIE FP2 2018 Q10 [12]}}