The authors describe a compositional perceptual mapping procedure, unr
estricted attribute-elicitation mapping (UAM), which allows consumers
to describe and rate the brands in their own terminology and thus rela
xes the restrictive assumptions of traditional compositional mapping t
echniques regarding the structure and interpretation of the set of att
ributes. They compare the performance of three estimation techniques f
or constructing a group space based on the idiosyncratic data, namely,
INDSCAL, CANCOR, and generalized procrustes analysis (GPA). Their fin
dings indicate that the three estimation techniques perform about equa
lly well. UAM also is compared with traditional compositional mapping.
They find that UAM is superior on fit of the solution, interpretabili
ty, and sample reliability. UAM probably holds an edge with respect to
data collection. Traditional compositional mapping is superior on eas
e of data analysis. No major difference was found on predictive validi
ty and structural reliability.