Abstract: The concepts of mediator and related constructs, as well as the estimation of mediating effects were discussed. Based on the comparison of various testing methods, a procedure was proposed which was a composite test derived from two existing testing methods. The newly proposed procedure is likely to be better than any single testing method in terms of the sum of type 1 and type 2 error rates. Moreover, it can be used to test both partial and full mediating effects. As an illustration, the procedure was applied to an empirical study on students’ antisocial behaviors and their effects on peer relations.

Key words: mediator, test, type 1 error rate, power, peer relation