Desktop Loglinear Modelling

This didactic paper is intended as a guide to the use of microcomputer statistical analysis packages for researchers who have selected loglinear analysis as appropriate for their problem. It is assumed that readers will be familiar with the statistical theory of loglinear analysis as treated in Kennedy (1988) and Busk and Marascuilo (1989). The first part of this paper describes the application of one popular package to a fairly straightforward problem. This is followed by a critical survey of the features available in four of the leading packages. A discussion of the survey's findings and some suggestions for further development are included.

Item Parameter Estimation Via Marginal Maximum Likelihood and an EM Algorithm: A Didactic

The Bock and Aitkin (1981) Marginal Maximum Likelihood/EM approach to item parameter estimation is an alternative to the classical joint maximum likelihood procedure of item response theory. Unfortunately, the complexity of the underlying mathematics and the terse nature of the existing literature has made understanding of the approach difficult. To make the approach accessible to a wider audience, the present didactic paper provides the essential mathematical details of a marginal maximum likelihood/EM solution and shows how it can be used to obtain consistent item parameter estimates. For pedagogical purposes, a short BASIC computer program is used to illustrate the underlying simplicity of the method.