THE PRECISION OF DATA OBTAINED IN LARGE-SCALE SCIENCE ASSESSMENTS - AN INVESTIGATION OF BOOTSTRAPPING AND HALF-SAMPLE REPLICATION METHODS

Powerful computational procedures are now available to better determin e the accuracy of statistical estimates derived from data that have un known distributions or do not meet parametric requirements. These tech niques are generally called resampling plans and include the recently developed bootstrap. Science educators often face the problem of nonno rmal distributions especially when conducting large-scale assessments or evaluating national curriculum projects that require complex sampli ng plans. Resampling techniques permit the researcher to make inferenc es without the strong distributional assumptions needed for more tradi tional parametric approaches. In this study, the bootstrap and a simpl ified version of a half-sample replication are used to examine the pre cision of science test scores obtained in a large-scale evaluation of Scope, Sequence, and Coordination, a national science curriculum proje ct. The resampling plans are described in some detail and the results are compared with those obtained from parametric methods. (C) 1998 Joh n Wiley & Sons, Inc.