@BOOK{NAP23616, author = "National Academies of Sciences, Engineering, and Medicine", title = "Refining the Concept of Scientific Inference When Working with Big Data: Proceedings of a Workshop—in Brief", doi = "10.17226/23616", abstract = "Big Data \u2013 broadly considered as datasets whose size, complexity, and heterogeneity preclude conventional approaches to storage and analysis \u2013 continues to generate interest across many scientific domains in both the public and private sectors. However, analyses of large heterogeneous datasets can suffer from unidentified bias, misleading correlations, and increased risk of false positives. In order for the proliferation of data to produce new scientific discoveries, it is essential that the statistical models used for analysis support reliable, reproducible inference. The National Academies of Sciences, Engineering, and Medicine convened a workshop to discuss how scientific inference should be applied when working with large, complex datasets.", url = "https://nap.nationalacademies.org/catalog/23616/refining-the-concept-of-scientific-inference-when-working-with-big-data", year = 2016, publisher = "The National Academies Press", address = "Washington, DC" }