Assessing the Assumptions Behind the IAT

Posted: 31 Mar 2008

See all articles by Peter Stüttgen

Peter Stüttgen

Carnegie Mellon University - David A. Tepper School of Business

Joachim Vosgerau

Bocconi University

Peter Boatwright

Carnegie Mellon University - David A. Tepper School of Business

Date Written: March 2008

Abstract

When researchers use the Implicit Association Test (IAT), they tacitly assume that attitudes towards the two target categories are strongly negatively correlated. We show that this assumption is likely to be violated in marketing contexts. As a consequence, IAT-scores are potentially invalid measures of implicit consumer attitudes. We demonstrate this by simulating possible correlation matrices of the underlying implicit attitudes and the IAT measurements, and then calculating the resulting IAT validity. We find that when the tacit assumption is satisfied the IAT validity is reasonably high. However, when the tacit assumption is violated (i.e., attitudes towards the two target categories are positively correlated), IAT validities are so dispersed that it is practically impossible to meaningfully interpret the IAT. We conclude by giving guidelines for how researchers may try to avoid violations of the assumption of the IAT.

Keywords: Implicit Association Test, measurement validity, simulation

Suggested Citation

Stüttgen, Peter and Vosgerau, Joachim and Boatwright, Peter, Assessing the Assumptions Behind the IAT (March 2008). Available at SSRN: https://ssrn.com/abstract=1114208

Peter Stüttgen (Contact Author)

Carnegie Mellon University - David A. Tepper School of Business ( email )

5000 Forbes Avenue
Pittsburgh, PA 15213-3890
United States

Joachim Vosgerau

Bocconi University ( email )

Via Sarfatti, 25
Milan, MI 20136
Italy

Peter Boatwright

Carnegie Mellon University - David A. Tepper School of Business ( email )

5000 Forbes Avenue
Pittsburgh, PA 15213-3890
United States

Register to save articles to
your library

Register

Paper statistics

Abstract Views
483
PlumX Metrics