This study examined the effect of alternative scale formats on reporti
ng of intensity of attitudes on Likert scales of agreement. A standard
one-stage format and an alternate two-stage format were tested in thr
ee separate studies on samples of university students in three countri
es. In general, the two-stage format generated the greatest percentage
of extreme-position (i.e. most intense) responses across scales. A te
st of predictive ability showed that the two-stage format was a better
predictor of product preferences. Underlying data structures did not
differ much between the two.