Thissen and Wainer (EJ 284 848) suggested that the introduction of a prior distribution for the lower asymptote may alleviate problems of a large standard error of the location parameter of the three parameter logistic model. The correctness of this suggestion is demonstrated in detail. (Author/BW)

Empirical Bayes methods are shown to provide a practical alternative to standard least squares methods in fitting high dimensional models to sparse data. An example concerning prediction bias in educational testing is presented as an illustration. (Author)