Linear equating methods for the common-item non-equivalent populations design were compared when true-score correlation between the test and anchor was less than unity. Scores from two groups of approximately 300 examinees illustrated three methods: (1) the Tucker equating method; (2) the Angoff-Levine method; and (3) the Congeneric-Levine method.…

This note shows that, under conditions specified by Levin and Subkoviak (TM 503 420), it is not necessary to specify the reliabilities of observed scores when comparing completely randomized designs with randomized block designs. Certain errors in their illustrative example are also discussed. (Author/CTM)

Comments (TM 503 706) on an earlier article (TM 503 420) concerning the comparison of the completely randomized design and the randomized block design are acknowledged and appreciated. In addition, potentially misleading notions arising from these comments are addressed and clarified. (See also TM 503 708). (Author/CTM)

This note continues the discussion of earlier articles (TM 503 420, TM 503 706, and TM 503 707), comparing the completely randomized design with the randomized block design. (CTM)

A correction procedure for estimating correlation coefficients when faced with the problem of a restricted range in the variables due to an explicit selection procedure was empirically investigated. Results indicated that the assumption of linearity is critical, but that homoscedasticity is less important. (JKS)

The relationship between anxiety and learning was examined within the context of drive theory and trait-state anxiety theory. Results indicated that trait anxiety had a causal influence on state anxiety and on test performance. The possibility of a reciprocal relationship between state anxiety and performance was suggested. (Author/BH)