Standards-Setting Procedures in Accountability Research: Impacts of Conceptual Frameworks and Mapping Procedures on Passing Rates.

Standard-setting research has yielded a rich array of more than 50 standard-setting procedures, but practitioners are likely to be confused about which to use. By synthesizing the accumulated research on standard setting and progress monitoring, this study developed a threedimensional taxonomy for conceptualizing and operationalizing the various procedures: outcome versus growth assessment, theory-driven versus datadriven approach, and observed scale versus latent scale mapping.An empirical study is reported to illustrate how these various approaches can be implemented to meet the accountability challence in the No Child Left Behind era. Consistency analysis of 12 standard-setting procedures reveals vastly disparate pass/fail decisions among different procedures, even within the same conceptual framework or mapping operation. Particularly disturbing is the finding that the passing rate may jump from as low as 29% to as high as 79%, depending on whether the standard is mapped to the obserVed-score scale or the latent-score scale. Implications and future directions for policy makers, school officials, and psychometricians are discussed. (Contains 9 tables and 107 references.) (Author/SLD) Reproductions supplied by EDRS are the best that can be made from the original document.