Dear Dr. Kirk:
I have a question about using a rubric...We have several tasks that we would like students in different programs to do. The tasks would be the same in that the same kind of questions would be asked and the same kind of projects would be done. However, they would be specific to each program (for example - early childhood activities look different from elementary children activities). If we use a task-specific rubric, would the results give us valid score-based inferences?
You might check out this article by Barbara M. Moskal and Jon A. Leydens (Colorado School of Mines). As they note:
Although many teachers have been exposed to the statistical definitions of the terms "validity" and "reliability" in teacher preparation courses, these courses often do not discuss how these concepts are related to classroom practices...One purpose of this article is to provide clear definitions of the terms "validity" and "reliability" and illustrate these definitions through examples. A second purpose is to clarify how these issues may be addressed in the development of scoring rubrics. Scoring rubrics are descriptive scoring schemes that are developed by teachers or other evaluators to guide the analysis of the products and/or processes of students' efforts. The ideas presented here are applicable for anyone using scoring rubrics in the classroom, regardless of the discipline or grade level.
Does anyone else have suggestions or resources on determining the validity of a rubric?