A method is presented to use school-level attributes in sample description and random assignment of schools to conditions in drug prevention programs. Utility of archival data was examined using multivariate canonical techniques, and it was found that a small set of data could predict observed variations in drug use. (SLD)

A study was made to ascertain how large a sample is needed to make media effectiveness decisions which are generalizable to the total educable mentally handicapped (EMH) population. The method employed in the study involved pretesting and posttesting a sample of 70 primary and intermediate EMH children on the content of a filmstrip. Statistical…

Accurate estimation of variance components used in generalizability theory is essential for the theory to be viewed as an efficacious mechanism for studying the reliability and validity of a measurement procedure. This paper explores two alternatives for dealing with the apparent instability of small sample size used in determining the accuracy of…

In response to a mandate from the California State Legislature, the California Board of Corrections conducted a three-phase research study in preparation for the revision and standardization of the current state standards for hiring and training corrections personnel. The primary focus of the second phase of the project was on the development and…