Question
(i) Give one advantage and one disadvantage of using a box-and-whisker plot to represent a set of data. [2]
(ii) The times in minutes taken to run a marathon were recorded for a group of 13 marathon runners and were found to be as follows.
180 275 235 242 311 194 246 229 238 768 332 227 228
State which of the mean, mode or median is most suitable as a measure of central tendency for these times. Explain why the other measures are less suitable. [3]
(iii) Another group of 33 people ran the same marathon and their times in minutes were as follows.
190 203 215 246 249 253 255 254 258 260 261
263 267 269 274 276 280 288 283 287 294 300
307 318 327 331 336 345 351 353 360 368 375
(a) On the grid below, draw a box-and-whisker plot to illustrate the times for these 33 people.
[4]
(b) Find the interquartile range of these times. [1]
Mark scheme
6(i) Advantage: comment referring to spread or range or shape B1 Comments referring to quartiles, IQR, Range, median, shape, skewness,
data distribution, spread score B1
Any comments with reference to mean or standard deviation or any other
‘disadvantage’ will score B0
Comments referring to ‘5-value plot’, comparison with another data set,
overview or ease of drawing/plotting/reading require an appropriate
advantage statement.
Disadvantage: comment referring to limited data information B1 Comments referring to no individual data, no information about the
provided number of values, unable to calculate mean, standard deviation, variance
and mode score B1
Any comments with reference to median, shape or any other ‘advantage’
will score B0
Comments referring to ‘size of data set’ or ‘average’ require an
appropriate disadvantage statement.
Comments referring to outliers are ignored in all cases (as outliers are not
in the syllabus content) unless supported by an appropriate advantage /
disadvantage statement.
If comments not clearly identified, assume first comment is the advantage.
2
6(ii) Not mean as data skewed by one large value B1 Comment which identifies 768 (or ‘a very large number’) as the problem.
Condone the use of ‘outlier’
Not mode as frequencies all the same B1 Comment which indicates that no mode exists
(e.g. all the data is different, there is no repeated number, all the values are
different)
Median B1 Median identified as choice, dependent upon statements for mean and
mode being given, even if incorrect or very general.
SC: Mean is identified as most suitable
Not mode as frequencies all the same SCB1 Comment which indicates that no mode exists
Not median as not all values used SCB1 Comment which indicates limitation of median e.g. median is not in
middle of range.
3
6(iii)(a) LQ = 256 or 256.5 Med = 280 UQ = 329 B1 Median, UQ and LQ values seen, may not be identified or identified
Min 190 max 375 correctly. (Not read from box plot unless value stated)
B1 FT Median and quartiles plotted in box on graph, linear scale
150 200 250 300 350 400 B1 Correct end points, whiskers from ends of box but not through box, not at
time minutes top or bottom of box
B1 Uniform scale from 190 to 375 (need at least 3 linear identified points
min) and labelled ‘time’ and ‘minutes’ (can be in title)
No time axis or time axis with no scale attempt, Max B1B0B0B0
4
6(iii)(b) IQR = their 329 – their 256 = 73 or 72.5 B1 FT Must follow through only from their stated values (condone if correct
quartiles stated here), not reading from graph.
1