Faulty assumptions: A comment on Blanton, Jaccard, Gonzales, and Christie (2006)

Abstract

Blanton, Jaccard, Gonzales, and Christie (BJGC, 2006) assert that the Implicit Association Test (IAT) imposes a model that portrays relative preferences as the additive difference between single attitudes. This assertion is misplaced because relative preferences do not necessarily reduce to component attitudes. BJGC also assume that the IAT conditions represent two indicators of the same construct. This assumption is incorrect, and is the cause of their poor-fitting models. The IAT, like other experimental paradigms, contrasts performance between interdependent conditions, and cannot be reduced to component parts. This is true whether calculating a simple difference between conditions, or using the IAT D score. D - an individual effect size that is monotonically related to Cohen's d - codifies the interdependency between IAT conditions. When their unjustified psychometric assumptions are replaced with plausible assumptions, the models fit their data very well, and basis for their poor-fitting models becomes clear.

Figures

Figure 1

Structural models for combining items (top) and contrasting conditions (bottom) with four indicators (a,b,c,d) for each condition (1, 2), where the effect is represented as a difference score (Condition1 – Condition2). The combining items model assumes that (a) the subtraction reverse codes Condition2 scores to match scale interpretation with Condition1 (e.g., higher values=more of construct), (b) conditions can be decomposed, and (c) both conditions are indicators of a single construct. The contrasted conditions model assumes that (a) scale interpretation is matched before subtraction occurs, (b) the conditions cannot be decomposed meaningfully, and (c) the construct is revealed by the comparison of interdependent conditions.

Figure 2

Structural equation model of a latent math-arts attitude IAT factor predicting math identity.

Figure 3

Structural equation model of a latent math-arts attitude IAT factor predicting math identity accounting for variance in IAT indicators shared with general processing speed.