Looking Past the Claims: a Psychometric Analysis of the Implicit Association Test

I examine the theory, methods and analytic strategies surrounding the IAT to determine the psychometric model that a researcher embraces (knowingly or unknowingly) whenever this measure is used. This analysis reveals a causal model that is unusually restrictive, a measurement model that is not empirically supported, and a set of measurement assumptions that are typically violated. This framework can help explain why IAT scores might have undesirable test properties and it points to potential misapplications of the measure in marketing contexts. Recent attempts to address these limitations like new scoring algorithms introduce systematic confounds. Alternative new methods are suggested.

Citation:

Hart Blanton (2009) ,"Looking Past the Claims: a Psychometric Analysis of the Implicit Association Test", in NA - Advances in Consumer Research Volume 36, eds. Ann L. McGill and Sharon Shavitt, Duluth, MN : Association for Consumer Research, Pages: 38-40.