The fact that the shorter scale has low internal consistency doesn't necessarily
mean that the 4 items in question are not unidimensional. It may just be that
the measurement error is large relative to their covariance. Given that the
four items in question are drawn from a scale with established internal
consistency, I'd suspect they probably are measuring the same thing - only not
measuring it very well.
purnima.
To:
cc:
From: John Donovan <[EMAIL PROTECTED]>/
Date: 12/07/99 01:09:40 PM
Subject: Re: Scale Reliability
Brett -
Although you may have a conceptual reason for summing the four item scores to
form a composite, the low level of internal consistency that these items display
suggests that they may not be assessing a unitary construct. So, to sum these
four items and label this score as a single variable or construct (locus of
control?) may be problematic. Have you assessed the dimensionality of these
items? If you find that these items do not strongly load on a single, unitary
factor, you may want to consider breaking the items up, rather than summing
them.
John
