Abstract
In this article, it is shown how one can estimate latent means in panel analysis. It is shown how simultaneous estimation of latent location parameters in different groups can be obtained and how latent means can be recalculated using the location parameters along with the stability coefficients. Latent means for attitudes toward guestworkers in Germany are computed for gender, age, and education and are compared with the means from composites based on the observed item means.
Get full access to this article
View all access options for this article.
