Multivariate Logistic Regressions Using Orthogonalized Residuals Performs multivariate logistic regressions by way of orthogonalized residuals. As a special case, the methodology recasts alternating logistic regressions in a way that is consistent with standard estimating equation theory. Cluster diagnostics and observation level diagnostics such as leverage and Cook's distance are computed based on an approximation. Exact versions of these diagnostics are computationally demanding and as of this version, will not be included. Software Depends: methods Kunthel By <kby@bios.unc.edu> Kunthel By, Bahjat F. Qaqish, and John S. Preisser GPL (>= 2) 2011-01-25 application/tgz http://CRAN.R-project.org/package=orth