Using simulation, studied the influence of each of 12 imputation methods and 2 methods using the EM algorithm on the results of maximum likelihood factor analysis as compared with results from the complete data factor analysis (no missing scores). Discusses why EM methods recovered complete data factor loadings better than imputation methods. (SLD)

A generalized Rasch model is presented for measuring attitudes; it is based on the concepts of Thurstone's method of successive intervals. Benefits of the model are illustrated with a study of students' (N=4,035 fifth through ninth graders) interest in physics. (SLD)

This paper examines a data set that has its origins in European Social Fund Objective 4 financed training programmes in small- to medium-sized enterprises (SMEs) in Britain to examine the extent to which three different personal development outcomes are attributable to different types of skills acquired during the training process. The three…

The factor structure, psychometric properties, and relationship with personality variables of a Spanish version of the Savings Inventory-Revised (SI-R) are investigated in a sample of 381 undergraduate students. A maximum likelihood factor analysis suggests a three-factor structure, which is similar but not identical to that of the original…

The self-report Educational Beliefs Questionnaire (EBQ) was constructed, and its construct validity was studied with 610 elementary school and secondary school teachers. The instrument assesses beliefs about five specific educational concepts. Further research will determine whether the 3-factor model still applies to a 20-item version of the EBQ.…