Assessing the Assumptions Behind the Iat

Peter Stuettgen, Carnegie Mellon University, USA
Peter Boatwright, Carnegie Mellon University, USA
The calculation of the IAT-effect assumes a certain correlational structure between the attitudes to be measured. We argue that this assumption is likely to be violated in marketing contexts, since consumers often have attitudes of similar valence to different products within the same category. Since correlations of the implicit attitudes are unobservable, we use simulations to examine the importance of this assumption for the validity of the IAT. We find that the assumption is crucial, in that if it is violated (satisfied) the IAT’s validity is low (high) despite high (low) accuracy of the response latencies.
[ to cite ]:
Peter Stuettgen and Peter Boatwright (2009) ,"Assessing the Assumptions Behind the Iat", in NA - Advances in Consumer Research Volume 36, eds. Ann L. McGill and Sharon Shavitt, Duluth, MN : Association for Consumer Research, Pages: 38-40.