In this study, we aimed to determine the latent structure of multiple EEG sleep variables in patients with major depressive disorder (MDD) and in healthy control subjects and to examine associations between sleep factors and clinical variables. Subjects included 109 women with MDD and 54 healthy control women. EEG sleep data were collected prior to any treatment. Principal components analysis (PCA) was conducted on a set of 24 sleep variables. Separate PCAs were run for patients with MDD, control subjects, and a matched group of patients and controls. Other analyses included correlations, t-tests and MANOVA. Each PCA identified four sleep factors that explained 70% of the total variance in individual sleep variables: slow wave sleep, REM sleep, sleep continuity and REM latency/delta sleep ratio (RL/DSR). Patients with MDD and healthy controls differed on the mean value of the sleep continuity factor, and a multivariate analysis of variance based on the PCA identified MDD-control differences in REM sleep and sleep continuity. In the MDD group, slow wave sleep correlated inversely with age and personality disorder symptoms; sleep continuity correlated with subjective sleep quality and anxiety; and RL/DSR correlated inversely with age. The mean value of the REM factor was higher among treatment non-responders than responders. EEG sleep variables have a similar latent structure in women with MDD and in healthy controls. These sleep factors are supported conceptually and empirically, and correlate with clinical measures in women with MDD. Multivariate statistical techniques decrease the risk of Type I and Type II errors when using a large number of collinear sleep measures, and can clarify conceptual issues related to sleep and depression.