IAL S1 representation of data: exam questions with mark schemes
Histograms (frequency density), stem-and-leaf, box plots, cumulative frequency, outliers, skewness; comparing distributions.
Each question carries its marks, and its mark scheme sits under it: M marks for method, A marks for accuracy, B marks for a correct result on its own. Try the question on paper first, then open the solution and mark yourself the way an examiner would.
Question 1
Explain the key difference between a bar chart and a histogram in terms of what they represent.
Show solution
- B1 for stating that a bar chart represents discrete or categorical data, while a histogram represents continuous grouped data.
- B1 for stating that in a bar chart, the height is proportional to frequency, whereas in a histogram, the area of the bar is proportional to frequency.
Question 2
For a data set, the lower quartile is
Show solution
- M1 for calculating the interquartile range (IQR)
. - M1 for calculating the outlier boundaries
and . - A1 for stating the limits as
and .
Question 3
Give one reason why it might be appropriate to remove an outlier from a data set (cleaning the data), and one reason why it might be inappropriate.
Show solution
- B1 for stating it is appropriate if the outlier is clearly an error in recording or measuring.
- B1 for stating it is inappropriate if the outlier is a genuine, legitimate observation that reflects natural variation.
Question 4
On a box plot, an outlier is marked with a cross. The lower whisker extends to
Show solution
- M1 for stating that outliers are identified using a specific rule (e.g.,
). - A1 for explaining that the upper whisker is drawn to the highest data value that is *not* an outlier (in this case,
). - A1 for explaining that the lower whisker is drawn to the lowest data value that is *not* an outlier (in this case,
).
Question 5
If the data set representing salaries has a median of £45,000 and an IQR of £15,000, and a new policy increases everyone's salary by
Show solution
- M1 for recognising that multiplying data by a scale factor scales both the median and the IQR by the same factor.
- A1 for calculating the new median:
. - A1 for calculating the new IQR:
.
Question 6
The following values are recorded:
Show solution
- M1 for finding the quartiles:
. , . - M1 for calculating
. - M1 for calculating the boundaries: Lower =
, Upper = . - A1 for identifying the outliers:
(since ) and (since ).
Question 7
A histogram is used to represent a data set. The class
Show solution
- M1 for identifying the class width as
. - M1 for calculating the frequency density:
. - M1 for finding the width of the required interval:
. - A1 for calculating the estimated frequency:
values.
Question 8
Two box plots, A and B, represent the test scores of two different classes. Box plot A has a median of
Show solution
- M1 for comparing the medians: Class B has a higher median score (
). - A1 for interpreting the median: On average, students in Class B scored higher than students in Class A.
- M1 for comparing the IQRs: Class A has a larger IQR (
). - A1 for interpreting the IQR: The middle 50% of scores in Class A are more spread out (more variable) than those in Class B.
Question 9
A data set of
Show solution
- M1 for calculating the mean:
. - M1 for calculating the variance:
. - M1 for finding the standard deviation:
. - A1 for calculating the acceptable range:
to , which is to .
Question 10
A frequency polygon is drawn on top of a histogram. The points of the polygon are located at
Show solution
- M1 for recognising that the x-coordinates of the points represent the class midpoints, and the y-coordinates represent the frequency densities.
- M1 for deducing the class boundaries from the midpoints: assuming contiguous classes, the boundaries are
, , and . - M1 for identifying the class widths:
, , and respectively. - A1 for calculating frequencies by multiplying width by height (frequency density): Frequencies are
, , and .