|
EXCAT= extreme category adjustment = 0 |
Top Up Down
A A |
When using Rasch measures for prediction, slightly better results have been obtained when the measure estimates are based on adjusted data. A productive adjustment makes observations in extreme categories slightly less extreme.
EXCAT= 0 |
observations in the top and bottom categories of a rating scale or dichotomy are not adjusted |
EXCAT= 0.25 (or any value between 0 and 1) |
observations in the top and bottom categores are made more central by EXCAT= score points |
Example: EXCAT=0.25
Dichotomies: 0,1 data are analyzed as 0.25,0.75 data. The observed raw scores are the sums of these values. The category frequencies are: 0 becomes 0.75*0 and 0.25*1, 1 becomes, 0.25*0, 0.75*1.
Rating scale: 1,2,3,4 data are analyzed as 1.25,2,3,3.75 data. The observed raw scores are the sums of these values. The category frequencies are: 1 becomes 0.75*1 and 0.25*2, 4 becomes, 0.25*3, 0.75*4.