be able to draw conclusions about differences between the numbers (reflecting
how much a consumer prefers one brand over another), we must know some-
thing about the interval between the numbers. Since ordinal scales do not
provide that, interval scales can be used.
- Interval scalesare grounded on the assumption of equal intervals between the
numbers, i.e. the space between 5 and 10 is the same as the space between 45
and 50 and in both cases this distance is five times as great as that between 1
and 2 or 11 and 12, etc. Numbers indicate the magnitude of difference
between items, but there is no absolute zero point. Examples are attitude
scales and opinion scales – this scale would be able to measure how much a
consumer prefers one brand to another.
- Ratio scalesare the most powerful and possess all the properties of nominal,
ordinal and interval scales. In addition they permit absolute comparisons of
the objects, e.g. 6 m is twice as high as 3 m and six times as high as 1 m.
Numbers indicate magnitude of difference and there is a fixed zero point.
The personality approach 135
Box 7.3 Ordinal scales applied
Ordinal scales express consumers’ satisfaction or evaluation of one product
or one brand, e.g. ‘How satisfied are you with your current newspaper?’
Question Score 1–5
1 Not satisfied
2 Neither satisfied nor dissatisfied
3 Satisfied
4 Very satisfied
5 Extemely satisfied
Box 7.4 Interval scales applied
Interval scales express the standing of several brands in relation to each
other, e.g. ‘Assign the different beer brands according to the brand you
prefer the most:’ (assign the number 1 to the brand you prefer and assign the
number 5 to the brand you least prefer)
Brand Score 1–5
Miller’s
Coor’s light
Carlsberg
Budweiser
Heineken
