Cognitive tasks can be analyzed into cognitive components by using a s
ubtask design, with the subtasks representing the components. The mult
icomponent latent trait model (MLTM; Embretson, 1980, 1984) was used h
ere for three different tasks: providing a synonym for a stimulus word
(composite task), and generating and evaluating synonym candidates (s
ubtasks). The MLTM did not fit the synonym task data. Therefore, a heu
ristic evaluation procedure was developed that tested the important fe
atures of the model. This procedure provided explanations for why the
MLTM did not fit the data and, more importantly, which other new model
s would fit better.