Catherine S. Taylor
Theory of measurement; an examination of assumptions involved in test theory, errors of measurement, factors affecting reliability and validity, and item analysis and standards for educational and psychological tests. Prerequisite: EDPSY 490. Offered: Sp.
Students will learn classical test theory and the implications of classical test theory for strategies we use to gather evidence for the reliability of test and assessment scores as well as the validity of score interpretation and use. Students will also learn to be critical consumers of tests and assessments, as well as critics of the theory.
Student learning goals
General method of instruction
Most work will be hands on exploration with theory and data. There will be a minimum amount of lecture/demonstration. Small group work, discussion and problem-solving will constitute the majority of in-class time.
Review of basic statistical concepts of mean, variance, standard deviation, and correlation.
Class assignments and grading
There are four major assignments other than reading: a mid-term exam (open- note, open book) over the concepts and procedures of classical test theory; an item-test analysis project wherein students apply data analysis procedures to create and analyze a test (using an existing data base); and a test review project wherein students evaluate the quality of two tests. There is one thought paper over the history of classical test theory (based on readings)/
Students must pass the mid-term exam with a 2.7 or higher grade. If they do not, they must do an alternate form. Both projects have public directions and criteria and rubrics. Students are graded on rubrics for each project. Mid-term exam is 15% of grade; Item-test analysis is 25% of grade; Test review project is 35% of grade; contribution to small group work is 10% of grade; one thought paper over history of classical test theory is 15% of grade.