As environmental managers, we’re frequently asked to make judgements about the relative health of the environment. This is often difficult because, by its nature, the environment is highly variable in space and time. Ideally, such judgements should be informed by robust scientific investigation, or more precisely, the reliable interpretation of the resulting data.

Type I and Type II Errors

Even with robust investigations and good data, our interpretations can sometimes be wrong. In general, this happens when:

  • the investigation concludes that an impact has occurred, when in fact it hasn’t (Type I error)
  • fails to detect an impact, when an impact has actually occurred (Type II error).

Understanding the circumstances that lead to these errors is unfortunately complicated, and difficult unless you have a strong statistical background.

Forty-year old BACI (before-after-control-impact) designs are still one of the most appropriate designs for detecting impacts following a disturbance (natural or human-induced). They capture all the necessary spatial and temporal variances with a low risk of making a Type I error (false positive). The downside is that they’re complex, expensive to run, and can be prone to Type II errors (false negatives). These problems are more common in marginal biomes or those with high variability.

Managers must balance the risk of making a Type I error with the means for detecting an ecologically meaningful impact, if an impact has occurred. Navigating this trade-off is a demanding task for environmental managers, particularly because existing methods are costly and errors may have severe consequences for the environment, or proponents, who may face hefty fines in the event of Type I error.

The Benefits of epower

Faced with this dilemma, and with a growing sense of frustration in the lack of rigour applied to high profile environmental impact assessments, we developed a simple, robust and easy to use R package – ‘epower’ – for calculating the power of BACI designs. ‘epower’ allows users without a background in programming language, but with a basic knowledge of statistics, to run cost-benefit analysis for different BACI designs, to determine:

  • whether their design is suitably sensitive for a given effect size
  • whether the design can be simplified, or reduced in cost, without affecting the sensitivity of the assessment

‘epower’ was developed using an innovations grant from BMT. It’s freely available via GitHub and comes with a comprehensive manual. The ‘epower’ (V1.3) package is a BMT product which has been developed in collaboration among BMT, the Australian Institute of Marine Science, Queensland University of Technology and Pink Lake Analytics.

To find out more about epower, read our Methods in Ecology and Evolution article ‘‘epower’: an R package for power analysis of Before‐After‐Control‐Impact (BACI) designs