Research

My research interests are in the theory and practice of educational measurement. In recent years I have focused on performance-based measurement and policy issues in the use and interpretation of educational tests. My current research, supported by the Office of Educational Research and Improvement through the Center for Research on Evaluation, Standards, and Student Testing, is closely aligned with those interests.

Design of Educational Accountability Systems
My current research, funded by the U.S Department of Education, Office of Educational Research and Improvement, through the National Center for Research on Evaluation, Standards and Student Testing (CRESST), is focused on comparative analyses of alternative educational accountability systems. The particular focus is on alternative models for using student assessment data in longitudinal, quasi-longitudinal, or successive cohort designs. Alternative summarizations of student test scores, e.g., the percent of students scoring above a designated cut score, index scores based on weighted summaries of the number of students scoring in various score regions, and effect-size statistics based on scale scores are being investigated.

Impact of Educational Accountability Systems
My research on the impact of educational assessment and accountability systems is also supported through CRESST. In this research I am investigating the generalizability of gains in student performance reported by states. Assessment and accountability systems are increasingly focused on gains in performance. My research as well as that of other researchers has shown that gains can be seriously inflated under high-stakes conditions and underscores the need for careful validation of gains. The tools for evaluating gains, however, are weak. The current effort builds upon recent psychometric work that has extended traditional validation methods to address current issues raised by developments in assessment.