Some thoughts on the foundations of test score equating
(English)Manuscript (preprint) (Other academic)
Even if there is a general agreement on the basic idea behind test score equating, and also some consensus behind the requirements of test score equating, a number of different definitions can be found in the literature. One purpose of this paper is to present some of these definitions and discuss the similarities and differences between them. Another purpose is to present two of the most frequently used functions, the equipercentile equating function and the item response theory (IRT) true score equating function, and to discuss the connections between these functions and the different definitions. A conclusion is that it is important to understand the difference between an approach where the starting point is the stochastic individual whose answer on an item is governed by some probability distribution and an approach where the starting point is a distribution of potential scores in a population of individuals. This distinction is behind some of the differences between the definitions of equating, and also of importance for the entire equating process.
observed scores, true scores, item response theory, equating function
Probability Theory and Statistics
Research subject Statistics
IdentifiersURN: urn:nbn:se:umu:diva-32773OAI: oai:DiVA.org:umu-32773DiVA: diva2:305730