scientific article; zbMATH DE number 1763378

From MaRDI portal
Publication:4539030





The book under review introduces to the theory and practice of mental measurement, based on item responses. A mental `latent' attitude or ability (e.g. transitive reasoning ability), say theta, has to be measured, based on answers given by the subject to questions/items designed by the researcher. In the case of binary, correct/incorrect possible answers, the basic result is that if the probability \(P(\theta;i)\) of correct answer increases with theta for all items \(i\) proposed, then different individuals can be (first-order stochastically) ordered by the total number of correct answers. If moreover different functions \(P(\theta;i)\) and \(P(\theta;j)\) do not cross, also the items can be ordered, on a `difficulty' scale. Nonparametric item response theory only assumes the above monotonicity of the \(P\) functions; parametric models assume specific, usually logistic, functional forms. The advantage of the former approach -- which the book is about -- is that items whose corresponding \(P\) functions do not fit a particular functional form but are nonetheless monotonic can be admitted, leading to a more precise final measurement result. The book includes worked out examples, and in the final part deals with items which call for many-valued (rather than two-valued) possible answers.




Cited in
(38)








This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4539030)