This project was funded by the Nuffield Foundation, but the views exp ressed are those of the authors and not nec essarily those of the Foundation.
Measures of Central Tendency are ways of working out the most representative or central value
within a data set.
For the examples below, the following data set will be used.
8 12 3 5 23 19 14 8 6 16 10 8 13 9 27 16 2 9 5
Distances (in km) that interviewees travelled to access the High Street of Town A.
______________________________________________________________________________
Mode
The mode for a set of data is that which occurs most frequently within the set.
When the example data set is put in value order, one can see that the mode is 8 km.
2 3 5 5 6 8 8 8 9 9 10 12 13 14 16 16 19 23 27
It is important to remember when using the mode that it does not always represent the centre of a
distribution. Equally, identifying the mode is not always possible for all data sets – continuous data
for example may produce a mode that is meaningless as there may be one frequency of every
value. In some data sets there may be more than one mode, making the use of this analysis
impractical.
Median
The median is the middle value when the data set is placed in value order. If there are an odd
number of values in the data set, the middle value is taken as the median. If there are an even
number of values in the data set, the mid-point between the two middle values is taken as the
median.
When the example data set is put in value order, one can see that the median is 9 km.
2 3 5 5 6 8 8 8 9 9 10 12 13 14 16 16 19 23 27
Identifying the median is only possible when the data set can be ordered, but using the median can
offset the possible problems associated with outliers and anomalous data values.
4a – A Guide to
Measures of
Central Tendency
