The Information Matrix in Latent-Variable Models
Robert J. Mislevy, Kathleen M. Sheehan · 1988
The information matrix for the parameters in a latent-variable model is bounded from above by the information that would obtain if the values of the latent variables could also be observed.The difference is the "missing information."This paper discusses the structure of the information matrix, and characterizes the degree to which missing information can be recovered by exploiting collateral variables for respondents.The results are illustrated with data from the Armed Services Vocational Aptitude Battery reported in the survey Profile of American Youth.An appendix presents a heuristic argument in support of a large sample result in the paper.(Contains 7 tables and 13 references.)