Statistical test theory for the behavioral sciences

摘要

Test theory can be viewed as a collection of techniques for evaluating the development and use of specific tests in the behavioural sciences. Therefore, a course in test theory should help students become aware of the logic and mathematical models that underlie standard practices in test use and construction [1]. When dealing with statistical test theory, most authors distinguish between classical test theory and item response theory or modern test theory. The two paradigms are consistent and complementary with differences in the strength of assumptions, simplicity of computation, comparability of item and ability of an individual, and dependability of parameters on samples or tests. This book provides readers with an opportunity to gain insight into selected test theories in classical test theory and models in item response theory that are applied in the behavioural sciences.