The study of sleep, and in particular electroencephalogram (EEG)‐sleep recordings, is important in several areas of medicine. Next to pain, sleep anomalies are the most significant indicators of illness. During sleep the human brain goes through several physiological stages; therefore, the problem of automated detection of sleep stages usingEEGdata naturally arises in neurosciences. A two step procedure of computerized scoring of sleep stages is considered, with the first step involving features extractions via spectral and nonlinear dynamics characteristics and the second step in which sleep classifications can be accomplished.WIREs Comput Stat2013, 5:326–333. doi: 10.1002/wics.1261This article is categorized under:Statistical Learning and Exploratory Methods of the Data Sciences > Clustering and ClassificationApplications of Computational Statistics > Health and Medical Data/InformaticsApplications of Computational Statistics > Signal and Image Processing and CodingData: Types and Structure > Time Series, Stochastic Processes, and Functional Data