The two case studies used publicly available environmental data excerpted from the National Human Exposure Assessment Survey (NHEXAS) (https://github.com/USEPA/HEDS). These U.S. Environmental Protection Agency (EPA) Region 5 data were samples collected in 1995 to 1997 from the first visit, which removed temporal between-visit correlation from sites across Ohio, Michigan, Illinois, Indiana, Wisconsin, and Minnesota. The NHEXAS tap water sampling design distinguished original samples from quality control replicates, and all samples were analyzed in the same laboratory following EPA standard method 200.8 (version 4.4). The case studies analyze subsets of NHEXAS arsenic and chromium data that were selected to meet distributional assumptions and cannot be interpreted as NHEXAS analyses.

This dataset is associated with the following publication: Furman, M., K. Thomas, and B. George. Separating Measurement Error and Signal in Environmental Data: Use of Replicates to Address Uncertainty. ENVIRONMENTAL SCIENCE & TECHNOLOGY. American Chemical Society, Washington, DC, USA, 57(41): 15356-15365, (2023).