A Study of the Effect of the Violation of the Assumption of Independent Sampling Upon the Type I Error Rate of the Two-Group t-Test

Publisher Website
Google Scholar
Abstract
This paper describes some of the situations in which a psychologist is likely to violate the assumption of independent errors. A Monte-Carlo study of the effects of this violation is then described. A number of examples of different kinds and degrees of dependency are included along with a table that gives the effect of the dependency upon the shape of the test statistic's distribution. The results of this study demonstrate that this assumption is a critical one. Researchers are strongly urged to avoid hypothesis testing if they suspect that the assumption of independence has been violated.