| Exam Board | Edexcel |
|---|---|
| Module | S3 (Statistics 3) |
| Year | 2021 |
| Session | October |
| Marks | 12 |
| Paper | Download PDF ↗ |
| Mark scheme | Download PDF ↗ |
| Topic | T-tests (unknown variance) |
| Type | Two-sample z-test large samples |
| Difficulty | Standard +0.3 This is a standard two-sample t-test with straightforward calculations. Part (a) requires basic formulas for mean and variance from summary statistics, part (b) is a routine hypothesis test procedure, and parts (c)-(d) test standard theoretical knowledge. While it's a multi-part question worth several marks, each component follows textbook procedures with no novel problem-solving required, making it slightly easier than average. |
| Spec | 2.01a Population and sample: terminology5.05b Unbiased estimates: of population mean and variance5.05c Hypothesis test: normal distribution for population mean |
| \cline { 2 - 6 } \multicolumn{1}{c|}{} |
| \(\sum \boldsymbol { h }\) | \(\sum \boldsymbol { h } ^ { 2 }\) |
|
| ||||||||
| Exercise regularly | 50 | 3270 | 214676 | \(\alpha\) | \(\beta\) | ||||||||
| 40 | 2832 | 201660 | 70.8 | 29.6 |
| Answer | Marks | Guidance |
|---|---|---|
| Answer/Working | Mark | Guidance |
| \(\bar{h} = 65.4\) | B1 | 65.4 only |
| \(s^2 = \frac{214676 - 50\times(\text{"65.4"})^2}{49}\) | M1 | Correct method to find \(s^2\) using their \(\bar{h}\) |
| \(= 16.693\ldots\) | A1 | awrt 16.7 |
| Answer | Marks | Guidance |
|---|---|---|
| Answer/Working | Mark | Guidance |
| \(H_0: \mu_{\text{do}} = \mu_{\text{do not}}\), \(H_1: \mu_{\text{do}} < \mu_{\text{do not}}\) | B1 | Both hypotheses correct – must be clear which is exercise and which is not |
| \(z = \pm\frac{\text{"65.4"} - 70.8}{\sqrt{\frac{\text{"16.693"}}{50} + \frac{29.6}{40}}}\) | M1M1 | For the denominator (ft their 16.693); correct ft their 65.4 and 16.693 |
| \(= \pm5.21\ldots\) | A1 | awrt 5.21, allow \( |
| CV 1.6449 | B1 | \( |
| Amala's belief is supported | A1ft | ft their \(z\) value and CV if hypotheses are correct way round. May be in words with heart and exercise e.g. resting heart rate is lower in men who exercise regularly |
| Answer | Marks | Guidance |
|---|---|---|
| Answer/Working | Mark | Guidance |
| CLT enables you to assume that (the sampling distribution of the sample mean of) resting heart rate is normally distributed for both groups | B1 | For the idea both groups normally distributed. Allow sample sizes big enough for CLT to hold |
| Answer | Marks | Guidance |
|---|---|---|
| Answer/Working | Mark | Guidance |
| Each population/sample is independent or each male is independent of the other males | B1 | For identifying the need for the groups or males to be independent |
| Assume the \(\sigma_{\text{do}}^2 = s_{\text{do}}^2\) and \(\sigma_{\text{do not}}^2 = s_{\text{do not}}^2\) | B1 | Realising the \(\sigma^2 = s^2\) |
## Question 6:
### Part (a):
| Answer/Working | Mark | Guidance |
|---|---|---|
| $\bar{h} = 65.4$ | B1 | 65.4 only |
| $s^2 = \frac{214676 - 50\times(\text{"65.4"})^2}{49}$ | M1 | Correct method to find $s^2$ using their $\bar{h}$ |
| $= 16.693\ldots$ | A1 | awrt 16.7 |
### Part (b):
| Answer/Working | Mark | Guidance |
|---|---|---|
| $H_0: \mu_{\text{do}} = \mu_{\text{do not}}$, $H_1: \mu_{\text{do}} < \mu_{\text{do not}}$ | B1 | Both hypotheses correct – must be clear which is exercise and which is not |
| $z = \pm\frac{\text{"65.4"} - 70.8}{\sqrt{\frac{\text{"16.693"}}{50} + \frac{29.6}{40}}}$ | M1M1 | For the denominator (ft their 16.693); correct ft their 65.4 and 16.693 |
| $= \pm5.21\ldots$ | A1 | awrt 5.21, allow $|z| = 5.21\ldots$ |
| CV 1.6449 | B1 | $|CV| = 1.6449$ or better |
| Amala's belief is supported | A1ft | ft their $z$ value and CV if hypotheses are correct way round. May be in words with heart and exercise e.g. resting heart rate is lower in men who exercise regularly |
### Part (c):
| Answer/Working | Mark | Guidance |
|---|---|---|
| CLT enables you to assume that (the sampling distribution of the sample mean of) resting heart rate is normally distributed for both groups | B1 | For the idea both groups normally distributed. Allow sample sizes big enough for CLT to hold |
### Part (d):
| Answer/Working | Mark | Guidance |
|---|---|---|
| Each population/sample is independent **or** each male is independent of the other males | B1 | For identifying the need for the groups or males to be independent |
| Assume the $\sigma_{\text{do}}^2 = s_{\text{do}}^2$ and $\sigma_{\text{do not}}^2 = s_{\text{do not}}^2$ | B1 | Realising the $\sigma^2 = s^2$ |
6. Amala believes that the resting heart rate is lower in men who exercise regularly compared to men who do not exercise regularly. She measures the resting heart rate, $h$, of a random sample of 50 men who exercise regularly and a random sample of 40 men who do not exercise regularly. Her results are summarised in the table below.
\begin{center}
\begin{tabular}{ | l | c | c | c | c | c | }
\cline { 2 - 6 }
\multicolumn{1}{c|}{} & \begin{tabular}{ c }
Sample \\
size \\
\end{tabular} & $\sum \boldsymbol { h }$ & $\sum \boldsymbol { h } ^ { 2 }$ & \begin{tabular}{ c }
Unbiased \\
estimate of \\
the mean \\
\end{tabular} & \begin{tabular}{ c }
Unbiased \\
estimate of \\
the variance \\
\end{tabular} \\
\hline
Exercise regularly & 50 & 3270 & 214676 & $\alpha$ & $\beta$ \\
\hline
\begin{tabular}{ l }
Do not exercise \\
regularly \\
\end{tabular} & 40 & 2832 & 201660 & 70.8 & 29.6 \\
\hline
\end{tabular}
\end{center}
\begin{enumerate}[label=(\alph*)]
\item Calculate the value of $\alpha$ and the value of $\beta$
\item Test, at the $5 \%$ level of significance, whether there is evidence to support Amala's belief. State your hypotheses clearly.
\item Explain the significance of the central limit theorem to the test in part (b).
\item State two assumptions you have made in carrying out the test in part (b).
\end{enumerate}
\hfill \mbox{\textit{Edexcel S3 2021 Q6 [12]}}