bias 56
APPLICATION AREAS AND FURTHER READINGS
New Product Development
Calantone, Roger, and Cooper, Robert G. (1981). ‘New Product Scenarios: Prospects
for Success,’ Journal of Marketing, 45(2), Spring, 48–60.
Marketing Management
Griffin, Abbie, and Hauser, John R. (1992). ‘Patterns of Communication among
Marketing, Engineering and Manufacturing: A Comparison between Two New
Product Teams,’ Management Science, 38(3), March, 360–373.
Kohli, Ajay K., and Jaworski, Bernard J. (1990). ‘Market Orientation: The Construct,
Research Propositions, and Managerial Implications,’ Journal of Marketing, 54(2),
April, 1–18.
Business-to-Business Marketing
Hise, Richard T., O’Neal, Larry, McNeal, James U., and Parasuraman, A. (1989).
‘The Effect of Product Design Activities on Commercial Success Levels of New
Industrial Products,’ Journal of Product Innovation Management, 6(1), March, 43.
BIBLIOGRAPHY
Hultink, Erik Jan, and Hart, Susan (1998). ‘The World’s Path to the Better Mouse-
trap: Myth or Reality? An Empirical Investigation into the Launch Strategies of
High and Low Advantage New Products,’ European Journal of Innovation Manage-
ment, 1(3), December, 106–122.
bias
DESCRIPTION
In a measurement context, any situation where results or conclusions misrep-
resent what is being studied.
KEY INSIGHTS
Bias in measurement can take many forms. Aside from biases or errors
in the choice or implementation of a sampling method (e.g. where a
non-random sampling method is used as opposed to a random one),
there may also be observation biases where results do not reflect what
is observed or, alternatively, what is not observed. Bias from that which
is not observed includes non-response bias, where results are skewed as
a result of excessive non-response. In such an instance, results obtained
are not representative of what is being studied as a result of responses
obtained from respondents differing from that which would have been
obtained from non-respondents. Another form of bias is late response
bias which refers to bias in results due to responses of late respondents
differing from responses of early respondents.
Biases may also be associated with particular measurement methods. In
mail surveys, for example, respondents are able to see the entire survey
before answering any question. Such a situation has the potential for
what is referred to as sequence bias, where respondents’ replies to certain
questions are not independent but rather conditioned by knowledge of,
or responses to, other questions and where the result may be distortions
in the answers provided.
KEY WORDS Measurement, sampling, misrepresentation, error, surveys