Search
Program Calendar
Browse By Day
Browse By Time
Browse By Person
Browse By Room
Browse By Unit
Browse By Session Type
Search Tips
Annual Meeting Registraion, Housing and Travel
Personal Schedule
Sign In
The myriad of actual uses of test scores due to accountability systems requires a thoughtful discussion of fairness and methods for assessing fairness. Previous research has examined multilevel DIF frameworks as solutions for nested data structure, however, scant research has linked multilevel DIF frameworks to the need for social-unit level fairness evidence in an accountability context. To further the investigation of methodologies which support validation work at the social-unit level, three multilevel DIF frameworks were compared: (1) the Begg Mantel-Haenszel, (2) the SIBTEST BSSE, and (3) the three-level Rasch model. Power, Type I error, and effect size estimates were compared across various conditions.