June 2019 Statistics Q1
1. A sixth form college has 84 students in Year 12 and 56 students in Year 13
The head teacher selects a stratified sample of 40 students, stratified by year group.
The head teacher is investigating the relationship between the amount of sleep, \(s\) hours, that each student had the night before they took an aptitude test and their performance in the test, \(p\) marks.
For the sample of 40 students, he finds the equation of the regression line of \(p\) on \(s\) to be\[p = 26.1 + 5.60s\]
| Scheme | Marks | AO |
|---|---|---|
| Label each year group | B1 | 1.1b |
| Use random numbers to select a ... | B1 | 1.1b |
| Simple random sample of 24 Year 12s and 16 Year 13s. | B1 | 1.1b |
| (3) |
Notes
B1: for a suitable numbered/labelled/ordered(o.e.) list/database/register(o.e.) for each year group.
Condone poor numbering but if just one list, then the Year 12s must be distinguishable from the Year 13s
B1: for use of random numbers/sample/selection to choose students
B1: for 24 Year 12s, and 16 Year 13s
Note: A description of a systematic sample: only allow access to the first mark and therefore may score maximum B1B0B0
| Scheme | Marks | AO |
|---|---|---|
| Increase by 2.8 marks | B1 | 3.4 |
| (1) |
Notes
B1: Using the gradient of the regression equation must include increase(o.e.) and 2.8
‘Increase by approximately 3 marks’ is B0 but isw if 2.8 is seen
\(5.6 \div 2\) is not sufficient
| Scheme | Marks | AO |
|---|---|---|
| e.g. ‘the best performance is predicted for the students who never wake up’ | B1 | 3.5b |
| (1) | ||
| (5 marks) |
Notes
B1: for any suitable limitation of the model
e.g. the idea that the longer you sleep the better performance in the test
or only valid between 0 and 24 hours (within range of the data)
or only applicable to the amount of sleep the night before the test
or only takes sleep into consideration/does not include other variables (factors)
or cannot score below 26.1 marks on the test
or the model might not be linear over the entire range
or the model might predict more than the maximum mark
B0: e.g. might not be correlation between \(s\) and \(p\)
or individual student performance may vary