Question 1
18 marks
Reading times, outliers, regression and Spearman's rank correlation
- Statistics and probability
(a)
1 mark
Jason set a target of 10 students from each class, so he used quota sampling.
(b)
1 mark
The median is the line inside the box.
(c)
2 marks
The interquartile range is the upper quartile minus the lower quartile: and .
(d)
4 marks
- A value is an outlier if it is above .
- Since , Mackenzie's time is not an outlier, so Jason is correct.
(e)
1 mark
As the time to read the book increases, the exam percentage goes down: a negative correlation.
(f)
2 marks
Substitute into the equation.
(g)
2 marks
It's not reliable, because 1.5 hours is outside the range of times in the data, so this is extrapolation.
(h)
2 marks
Rank the number of pages with 1 as the largest, and the rating with 1 as the best.
(i)
3 marks
(i) The correlation of the two sets of ranks:
(ii) There is a moderate to strong positive association: books with more pages tend to have a better top-50 rating.

