The Scoring tab provides the options to perform scaled scoring and/or dichotomous classification.
The Scoring Options Tab
If your testing program reports scaled scores based on raw number-correct scores, these can be calculated. Scaled scores are computed using the scaling function (detailed below) for the total number correct scores and/or the domain number-correct scores. Scaled scoring is often used to mask details about the test, such as exact number of items or raw cutoff score, or to express scores on a different scale than number correct. Most large-scale tests use a form of scaled scoring.
- Linear scaling: The raw scores are first multiplied by the slope coefficient then the intercept is added to the product. For example, if you want the scores to be reported on a scale of 100 to 200 for a test of 50 items, the scaled score could be specified as SCALE = RAW × 2 + 100.
- Standardized scaling: The raw scores are converted to have a mean of X and a standard deviation of Y. This form of scaling is useful if you desire to center the mean of the test around a constant value for use in a report. For example, the classic IQ scale with mean=100 and SD=15.
If you want to perform dichotomous classification, such as pass/fail, click the box next to that statement. It is possible to classify based on either total number-correct or the scaled total number-correct scores. Enter the Cut-score, aka passing score or cut-point; the value at which scores are classified as in the high group. Scores below the cut-score are classified as being in the low group.