Although high annual disenrollments from prepaid group practices (PGPs) present significant problems to the manager, studies on this subject generally have been limited to simple descriptions of the phenomenon, The authors’ approach utilizes multivariate techniques—discriminant analysis and logistic regression—to overcome the simplicity of these bivariate studies. It allows an examination of the significant correlates of disenrollment in a stepwise manner that adjusts for the effects of all variables included in the models. Two surveys conducted by the Medical Care Group of St. Louis (MCGSL) provide data for this research. After classifying the sample of 2,402 families as continuous enrollees, voluntary disenrollees, and mandatory disenrollees, the analyses show that these groups represent significantly different member populations. The variables that significantly and independently discriminate among them include sociodemographic characteristics (subscriber age, race, education and occupation, and family size and income), satisfaction level with the plan, and presence of alternatives to the PGP (nonplan family members and coverage by alternative health insurance). These findings suggest that voluntary and mandatory disenrollment behavior may be more complex than previously considered. Moreover, the PGP manager is faced with perplexing problems in attempting to control this troublesome phenomenon.