assumptions of classical true score model
arnold on Sep 17, 2008
1) The mean of the error scores for a population of examinees is zero.
2) The correlation between true and error scores for a population of examinees is zero.
3) When examinees take two seperate tests and each examinee’s score on the two tests (or two testing occasions with the same form) are assumed to be randomly chosen from two independent distributions of possible observed scores, the correlation between error scores from the two testings is zero.
Reference: Crocker and Algina (1986), “Introduction to Classical & Modern Test Theory,” CBS College Publishing.
