A simulation study was conducted to evaluate the dependability of Stou
t's T index of unidimensionality as used in his DIMTEST procedure. DIM
TEST was found to dependably provide indications of unidimensionality,
to be reasonably robust, and to allow for a practical demarcation bet
ween one and many dimensions. The procedure was not affected by the me
thod used to identify the initial subset of unidimensional items. It w
as, however, found to be sensitive to whether the multidimensional dat
a arose from a compensatory model or a partially compensatory model. D
IMTEST failed when the matrix of tetrachoric correlations was non-Gram
ian and hence is not appropriate in such cases.