epower: An r package for power analysis of Before‐After‐Control‐Impact (BACI) designs

Abstract

Before‐After‐Control‐Impact (BACI) designs are widespread in environmental science, however their implicitly hierarchical nature complicates the evaluation of statistical power. Here, we describe epower, an r package for assessing statistical power of BACI designs. The package uses Bayesian statistical methods via the r‐package INLA to fit the appropriate hierarchical model to user supplied pilot survey data. A posterior sample is then used to build a Monte Carlo simulation to test statistical power specifically for the Before/After × Control/Impact interaction term in the BACI model. Power can be assessed for any number of user‐specified effect sizes for the existing design, or across a range of levels of replication for any part of the sampling design hierarchy. The package offers a user friendly robust approach for assessing statistical power of BACI designs whilst accounting for uncertainty in parameter values within a fully generalized framework.

Impacts of an Amazonian hydroelectric dam on frog assemblages

“…However, limited evidence indicated that those changes may have been happening in unflooded areas before dam closure. Stronger conclusions about these changes in species composition would be possible using a BACI design [ 74 ]. We recommend that environmental authorities require long-term monitoring and BACI designs in future environmental-impact studies.…”

A large-scale experiment finds no evidence that a seismic survey impacts a demersal fish fauna

“…We used a combination of MBACI and dose-response experimental designs (31) to monitor fishes within high-exposure (impact) and control sampling zones and at multiple sites that experienced varying levels of exposure to the seismic source within Area 3 (Fig. 1).…”

“…The MBACI sampling design provided a binary comparison between exposed and control zones (vessel control and control samples were pooled for analysis). The potential impact of exposure was measured as the difference in the response variable (e.g., abundance and length) before and after the seismic source exposure at a high-exposure (impact) zone, compared with the difference in the variable before and after the exposure at the vessel control and control zones (31). To demonstrate an impact, there must be statistical evidence for a significant difference in the measured variable between the high-exposure and control zones, after accounting for natural variability through time.…”

“…Abundance data were modeled using combined MaxN h −1 for each analysis group using the R package "Epower" (31) that implements a generalized Bayesian hierarchical-mixed MBACI analysis based on Laplace approximation via the integrated nested Laplace approximation (INLA) package (40). Epower provides a convenient means of specifying all elements of an MBACI design and provides an associated power analysis specifically for the BACI interaction term (31). Assessment of an impact is achieved by comparing two fitted Bayesian-generalized, linear-mixed models (one with and one without the BACI interaction term), with evaluation of the strength of evidence of a BACI interaction effect based on the posterior model probability of one model compared with the other.…”

Evaluating Impact Using Time-Series Data

“…Since most ecological time-series impact evaluation studies have focused on only one or a handful of time series [32][33][34][35][36][37], using only average change has not been a big problem, as each time series could be visually checked for indications of trends. However, risks increase when using large numbers of time series (e.g., counts of multiple bird species at multiple sites [38]), where checking individual series becomes impractical.…”