On the applications of the method of absolute scaling

Empirical and fictitious examples are described for investigating the applications of the absolute scaling method for item scaling and score scaling. A discrepancy between the correct values and the values estimated through the absolute scaling method is demonstrated. It is concluded that when the groups are different the assumption of an identity between test score conversion and item difficulty conversion is not met.Acknowledgment is due to Dr. Gulliksen, Dr. Lord, Dr. Swineford, and Dr. Tucker for their criticism and advice.