Education Commons^™

Mapping Student Achievement, Geoff Masters, Ray Adams, Jan Lokan

Prof Ray Adams

The analyses, publications and reports of quantitative data in education and the social sciences usually omit basic information on the construct measured. Probabilistic models for test data make it possible to delineate coherent and richly described measurement continua that facilitate interpretation of student achievement. The potential of conjoint measurement to bring about fundamental advances in educational testing practice lies in part in the opportunities it provides to build useful maps of learning domains and to use those maps in communicating student achievements. This chapter presents two applications of conjoint measurement aimed at constructing and describing achievement variables, developing insights into …

Response To 'Cautions On Oecd's Recent Educational Survey (Pisa), Ray Adams

Prof Ray Adams

This paper refers to the work of S J Prais who questioned the outcomes of the Organisation for Economic Cooperation and Development's PISA survey of the reading, mathematics and science attainments of fifteen year-olds. Prais suggested that methodological flaws in Programme for International Student Assessment (PISA) had resulted in an apparent improvement in the attainment of British students, particularly when compared to their Swiss and German counterparts. This paper responds to Prais's criticisms, noting that when Prais's conjectures are tested with empirical data they are not supported. The author argues that many of Prais's criticisms are due to an incomplete …

Measuring Student Knowledge And Skills : The Pisa 2000 Assessment Of Reading, Mathematical And Scientific Literacy, Andreas Schieicher, Claudia Tamassia, Geoff Masters, Ray Adams

Prof Ray Adams

Acer Conquest: Generalised Item Response Modelling Software, Margaret Wu, Ray Adams, M Wilson

Prof Ray Adams

ACER Conquest is a computer program for fitting item response and latent regression models. It provides a comprehensive and flexible range of item response models to analysts, allowing them to examine the properties of performance assessment, traditional assessments and rating scales. This manual examines ACER ConQuest in detail, includes a tutorial and coverage of technical matters.

Applications Of Item Response Theory In The Third International Mathematics And Science Study, E Gonzalez, Ray Adams, Marg Wu

Prof Ray Adams

The Third International Mathematics and Science Study (TIMSS) is a survey of mathematics and science achievement sponsored by the International Association for the Evaluation of Educational Achievement. With more than 45 participating countries, three target populations, more than thirty languages, 15,000 schools, more than half a million students, TIMSS is the largest and most ambitious international study of educational achievement ever undertaken. Students participating in the assessment were administered one of eight achievement tests that contain items in mathematics and science, using a variety of item formats. As TIMSS is an international study, many audiences will look at the results …

Rasch Models Of Multidimensionality Between Items And Within Items, W Wen-Chung, M Wilson, Ray Adams

Prof Ray Adams

This chapter focuses on Rasch measurement and extends it to multidimensional Rasch models. The author first clarifies multidimensionality at two levels: the item level and the test level. With this two way classification, three kinds of tests are formed: undimensional tests, multidimensional between-item tests, and multidimensional within-item tests. The author describes a multidimensional Rasch model, the multidimensional random coefficients multinomial logit (MRCML) model, for multidimensional tests. The model, when applied to multidimensional between-item tests, is more efficient than are unidimensional models in terms of model fit and reliability indices. The model can also be applied to investigate scale interaction of …

Bias In Weighted Likelihood Estimation When Using The Rasch Model, D Roberts, Ray Adams

Prof Ray Adams

There are three methods of maximum likelihood estimation that are commonly used with Rasch item response models: Joint maximum likelihood, which provides point estimates for both person and item parameters; conditional maximum likelihood, which produces estimates for the item parameters only, and marginal maximum likelihood, which produces estimates of the item parameters and parameters of the distribution from which it has been assumed that the persons have been sampled. A number of approaches have been suggested for obtaining ability estimates for subsequent use in reporting or analysis when either conditional or marginal methods have been used to obtain the item …