We establish a sufficient condition for the occurrence of nonresponse boundary solutions in a two-way square contingency table with nonignorable nonresponse. The condition depends only on the observed counts and thus it does not require computing the maximum likelihood estimates.

We consider maximum likelihood (ML) estimation of mean and covariance structure models when data are missing. Expectation maximization (EM), generalized expectation maximization (GEM), Fletcher-Powell, and Fisher-scoring algorithms are described for parameter estimation. It is shown how the...