CAIE Further Paper 4 2022 November — Question 6 9 marks

Exam BoardCAIE
ModuleFurther Paper 4 (Further Paper 4)
Year2022
SessionNovember
Marks9
PaperDownload PDF ↗
Mark schemeDownload PDF ↗
TopicT-tests (unknown variance)
TypeTwo-sample t-test equal variance
DifficultyStandard +0.8 This is a two-sample t-test with unequal sample sizes requiring calculation of pooled variance, manual computation of summary statistics from raw data, and proper hypothesis test execution. While methodical, it demands careful arithmetic, understanding of pooled variance formula, and correct application of t-distribution critical values—more demanding than standard single-sample tests but follows established procedures without requiring novel insight.
Spec5.05c Hypothesis test: normal distribution for population mean

6 A company manufactures copper pipes. The pipes are produced by two different machines, \(A\) and \(B\). An inspector claims that the mean diameter of the pipes produced by machine \(A\) is greater than the mean diameter of the pipes produced by machine \(B\). He takes a random sample of 12 pipes produced by machine \(A\) and measures their diameters, \(x \mathrm {~cm}\). His results are summarised as follows. $$\sum x = 6.24 \quad \sum x ^ { 2 } = 3.26$$ He also takes a random sample of 10 pipes produced by machine \(B\) and measures their diameters in cm. His results are as follows. $$\begin{array} { l l l l l l l l l l } 0.48 & 0.53 & 0.47 & 0.54 & 0.54 & 0.55 & 0.46 & 0.55 & 0.50 & 0.48 \end{array}$$ The diameters of the pipes produced by each machine are assumed to be normally distributed with equal population variances. Test at the \(2.5 \%\) significance level whether the data supports the inspector's claim.
If you use the following page to complete the answer to any question, the question number must be clearly shown.

Question 6:
AnswerMarks Guidance
AnswerMarks Guidance
\(s_x^2 = \frac{1}{11}\left(3.26 - \frac{6.24^2}{12}\right) = 0.001382\)M1 \(\frac{19}{13750}\), \(\frac{19}{15000}\)
\(s_y^2 = \frac{1}{9}\left(2.6124 - \frac{5.1^2}{10}\right) = 0.001267\)
Both correctA1 Both correct
\(s^2 = \frac{11 \times 0.001382 + 9 \times 0.001267}{12 + 10 - 2} = 0.001330\)M1 A1 Find pooled variance
\(t = \dfrac{\dfrac{6.24}{12} - \dfrac{5.1}{10}}{s\sqrt{\dfrac{1}{12} + \dfrac{1}{10}}} = 0.640\)M1 A1 Use correct formula for \(t\)
\(H_0: \mu_a = \mu_b \quad H_1: \mu_a > \mu_b\)B1
Critical value is \(2.086\) \((t_{0.975}(20))\)M1 Compare their calculated value with 2.086 and conclusion
\(0.640 < 2.086\)
Accept \(H_0\)
There is insufficient evidence to support inspector's claimA1 All correct except possibly B1, in context, level of uncertainty in language. 'Prove' scores A0
9Pooled variance not used: M1A1 M0A0 M0A0 B1 M1A0 max 4/9
## Question 6:

| Answer | Marks | Guidance |
|--------|-------|----------|
| $s_x^2 = \frac{1}{11}\left(3.26 - \frac{6.24^2}{12}\right) = 0.001382$ | M1 | $\frac{19}{13750}$, $\frac{19}{15000}$ |
| $s_y^2 = \frac{1}{9}\left(2.6124 - \frac{5.1^2}{10}\right) = 0.001267$ | | |
| Both correct | A1 | Both correct |
| $s^2 = \frac{11 \times 0.001382 + 9 \times 0.001267}{12 + 10 - 2} = 0.001330$ | M1 A1 | Find pooled variance |
| $t = \dfrac{\dfrac{6.24}{12} - \dfrac{5.1}{10}}{s\sqrt{\dfrac{1}{12} + \dfrac{1}{10}}} = 0.640$ | M1 A1 | Use correct formula for $t$ |
| $H_0: \mu_a = \mu_b \quad H_1: \mu_a > \mu_b$ | B1 | |
| Critical value is $2.086$ $(t_{0.975}(20))$ | M1 | Compare their calculated value with 2.086 and conclusion |
| $0.640 < 2.086$ | | |
| Accept $H_0$ | | |
| There is insufficient evidence to support inspector's claim | A1 | All correct except possibly B1, in context, level of uncertainty in language. 'Prove' scores A0 |
| | **9** | Pooled variance not used: M1A1 M0A0 M0A0 B1 M1A0 max 4/9 |
6 A company manufactures copper pipes. The pipes are produced by two different machines, $A$ and $B$. An inspector claims that the mean diameter of the pipes produced by machine $A$ is greater than the mean diameter of the pipes produced by machine $B$. He takes a random sample of 12 pipes produced by machine $A$ and measures their diameters, $x \mathrm {~cm}$. His results are summarised as follows.

$$\sum x = 6.24 \quad \sum x ^ { 2 } = 3.26$$

He also takes a random sample of 10 pipes produced by machine $B$ and measures their diameters in cm. His results are as follows.

$$\begin{array} { l l l l l l l l l l } 
0.48 & 0.53 & 0.47 & 0.54 & 0.54 & 0.55 & 0.46 & 0.55 & 0.50 & 0.48
\end{array}$$

The diameters of the pipes produced by each machine are assumed to be normally distributed with equal population variances.

Test at the $2.5 \%$ significance level whether the data supports the inspector's claim.\\

If you use the following page to complete the answer to any question, the question number must be clearly shown.\\

\hfill \mbox{\textit{CAIE Further Paper 4 2022 Q6 [9]}}