Impact Assessment: Assessing a Local Biological Effect With Before and After Data

Abstract

Abstract The design and analysis of monitoring studies to assess chronic biological effects of anthropogenic environmental change when data can be gathered before the change are discussed. Intervention Analysis compares Before and After time series at an Impact site. A special case, sometimes useful when the anticipated effects are “local,” is Before‐After, Control‐Impact (BACI), using comparison sites as covariates to reduce extraneous variance and serial correlation. Both sampling error and natural temporal processes cause uncertainty in inferences: both must be modeled. The models are themselves uncertain. The Impact site is not randomly selected, so these are observational studies, not experiments. Whether and how the change caused the “effects” must be based on their timing and on studies of mechanisms.