[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: intrarater reliability - anchoring stimuli


One way you could do it is gather data on one iteration of all the
fragments, and then do an item analysis, which basically predicts
performance on the full set from a reduced set.  You could eliminate items
until you get down to an acceptable test size,  with acceptable predictive
power for the full set.  Most statistical packages (I use Statistica) have
an item analysis module.