A Comparative Study of Classical Theory (Ct) and Item Response Theory (Irt) In Relation To Various Approaches of Evaluating the Validity and Reliability of Research Tools

Measurement theories are important to practice in educational measurement because they provide a background for addressing measurement problems. One of the most important problems is dealing with the Measurement Errors. A good theory can help in understanding the role of errors they play in measurement; (a) To evaluate the examinee's ability to minimize errors and (b) Correlations between variables. There are two theories addressing measurement problems such as test construction, and identification of biased test items: Classical Test Theory (CT) and Item Response Theory (IRT) (1950). As a result of a number of problems associated with the Classical Theory of Measurement, which cause inaccuracy in results i.e. methods and tools of measurement. There appeared a need to develop the methods of measuring behavior in a manner consistent with the Physical Measurement Methods. Based on the Philosophy of this measurement and assumption, which achieves the quality and safety of these methods, and acceptance of their results with a high Degree of Confidence. There were many research studies by professionals and those interested in behavioral measures, aimed and try to overcome some of the Behavioral Problems of Measurement. These studies have resulted in the emergence of Item Response Theory. Item response theory is a Statistical Theory about Items, Test Performance and abilities that are measured by Items. Item responses can be discrete or continuous and can be dichotomous and the item score categories can be ranked or non ranked . There can be one ability underlying test, and there are many models in which the relationship between item responses and the underlying ability can be specified. Within the IRT there are many models that have been applied to test data really but most famous among them is Racsh model. In this paper, both the theories i.e. Classical Test Theory and Item Response Theory (lRT) will be described in relation to approaches to measure the validity and reliability. The intent of this module is to provide a comparison of classical theory and item response theory.