In this paper we examine educational data whch has a cross-classified structure. A cross-classified value-added multilevel model is proposed for these data and the problem of estimation are discussed in relation to the probllem of an endogenous regressor.

The preliminaries in the paper contrast the advantages and disadvantages of using arbitrary scores for ordinal responses in linear models compared to generalised linear models for ordered catagory responses. The context of multilevel and random effects models is a particular focus. Simulation...

Modelling strategies for value-added multilevel models are examined. These types of models typically include an endogenous variable and this causes difficulties for the standard estimation techniques that are commonly used to analyse multilevel models. Two alternative estimation strategies are...

This paper first of all discusses some substantive and methodological issues concerned with disentangling the nature of effects in educational progress. We deal with criterion outcomes which are a limited set of ordered category grades for which multilevel generalised linear models are proposed.

Graded educational qualifications are commonly treated using arbitrary points scores in modelling educational progress. This paper discusses some of the problems of such pratices from statistical and substantive viewpoint. Random effects models of ordered categorisations are suggested as a...

The use of hierarchical models of educational effectiveness are reviewed. The paper also draws attention to the inedequacy of official performance indicators currently available and in particular the anattention to ressource issues.