As our understanding of hereditary and environmental contributors to disease expands, it is expected that more customized "personalized medicine" approaches will supplant traditional "one size fits all" diagnostic and therapeutic strategies. While big data analytics have been deployed extensively for applications in personalized medicine, small data studies for the myriad of data traces we each generate every day may further advance the methodological underpinnings of personalized medicine, with applications to personalized treatment choices and lifestyle decisions, and identification of personal risk factors and illness triggers. In this session, we discuss the design and analysis of small data studies, powered by personalized biostatistics to accommodate individual information needs and preferences, utilizing experimental methods such as N-of-1 trials, and non-experimental methods such as N-of-1 case-crossover designs. The session will facilitate a dynamic and timely inter-disciplinary exchange on the state-of-the-art and future directions of small data and personalized biostatistics. For further information, please see http://www.ucdmc.ucdavis.edu/chpr/preempt/ (tab Small Data).