Testing the Conditional Independence and Monotonicity Assumptions of Item Response Theory
- 1 September 1984
- journal article
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 49 (3) , 425-435
- https://doi.org/10.1007/bf02306030
Abstract
When item characteristic curves are nondecreasing functions of a latent variable, the conditional or local independence of item responses given the latent variable implies nonnegative conditional covariances between all monotone increasing functions of a set of item responses given any function of the remaining item responses. This general result provides a basis for testing the conditional independence assumption without first specifying a parametric form for the nondecreasing item characteristic curves. The proposed tests are simple, have known asymptotic null distributions, and possess certain optimal properties. In an example, the conditional independence hypothesis is rejected for all possible forms of monotone item characteristic curves.Keywords
This publication has 20 references indexed in Scilit:
- Characterizing the Manifest Probabilities of Latent Trait ModelsPsychometrika, 1983
- Odds ratio estimators when the data are sparseBiometrika, 1981
- Simultaneous Statistical InferencePublished by Springer Nature ,1981
- Dimensionality, bias, independence and measurement scale problems in latent trait test score modelsBritish Journal of Mathematical and Statistical Psychology, 1980
- Measures of Association for Cross ClassificationsPublished by Springer Nature ,1979
- Some odds ratio statistics for the analysis of ordered categorical dataBiometrika, 1974
- Linear Statistical Inference and its ApplicationsPublished by Wiley ,1973
- Fitting a Response Model for n Dichotomously Scored ItemsPsychometrika, 1970
- Association of Random Variables, with ApplicationsThe Annals of Mathematical Statistics, 1967
- A Simple Example of a Comparison Involving Quantal DataBiometrika, 1966