Personality
questionnaire results have little or no meaning unless
compared against what is ‘normal’ or 'typical' for a
large and relevant
sample of the wider population. Therefore, results
should always be plotted against a comparison
group (norm group) broadly related to the role
in question.
For example, a tool should be able to tell you "Meredith
describes herself as much less ambitious than is typical
for most managers and professionals".
By contrast, a test result presented as a stand alone
'score' is largely meaningless, and highly vulnerable to
misinterpretation.
Important: Statistically and practically, a norm group of 10,000
people is no better than a norm group of 1000 people. Why?
Because differences will be only fractions of a percent, which is entirely invisible when
plotted on a 10 or even 20 point scale. Nevertheless, some test publishers sell
the idea of large
norm groups as conferring a special advantage. They
do not. To suggest so is misleading and, perhaps, used to
redirect attention from the more important aspects of
design.
Much more
critical is the statistical construction of the tool you are
considering, in other words, the care
taken by the psychometricians when conducting the original research,
design and product testing.
