Outline
In a well-developed testing programme, the generation of raw scores from an assessment activity does not represent the end of the testing process. There are still questions to answer in relation to the accuracy and precision of these measurements and how they relate to the underlying construct. It is also important to choose and apply an appropriate method of classifying scores into appropriate categories (e.g. pass / fail) and ensuring these classifications are consistent in time and space. Appropriate methods for combing and reporting scores to candidates are also important considerations. Concepts are presented with examples and some practical exercises. Participation in ‘Workshop 1: An introduction to test construction’ would be beneficial but not compulsory.
- At the end of the workshop participants will be able to:
- List the main differences between Classical Test Theory (CTT) and Item Response Theory (IRT)
- Outline the generic processes involved in setting performance standards
- Outline some of the commonly used standard setting methodologies including their strengths and weaknesses
- Outline the main test equating models
- Describe how test scores are combined, scaled and reported
All courses are bookable on the Upcoming Courses page