Natural resource managers are developing assessments of selenium (Se) contamination in freshwater ecosystems based on fish tissue concentrations. We evaluated the effects of sample size (i.e., number of fish per site) on the probability of correctly detecting mean whole-body Se values above a range of potential management thresholds. We modeled Se concentrations as gamma distributions with shape and scale parameters fitting an empirical mean-to-variance relationship in data from southwestern West Virginia, USA (63 collections, 382 individuals). We used parametric bootstrapping techniques to calculate statistical power as the probability of detecting true mean concentrations up to 3mg Se/kg above management thresholds ranging from 4 to 8mg Se/kg. Sample sizes required to achieve 80% power varied as a function of management thresholds and Type I error tolerance (α). Higher thresholds required more samples than lower thresholds because populations were more heterogeneous at higher mean Se levels. For instance, to assess a management threshold of 4mg Se/kg, a sample of eight fish could detect an increase of approximately 1mg Se/kg with 80% power (given α=0.05), but this sample size would be unable to detect such an increase from a management threshold of 8mg Se/kg with more than a coin-flip probability. Increasing α decreased sample size requirements to detect above-threshold mean Se concentrations with 80% power. For instance, at an α-level of 0.05, an 8-fish sample could detect an increase of approximately 2 units above a threshold of 8mg Se/kg with 80% power, but when α was relaxed to 0.2, this sample size was more sensitive to increasing mean Se concentrations, allowing detection of an increase of approximately 1.2 units with equivalent power. Combining individuals into 2- and 4-fish composite samples for laboratory analysis did not decrease power because the reduced number of laboratory samples was compensated for by increased precision of composites for estimating mean conditions. However, low sample sizes (<5 fish) did not achieve 80% power to detect near-threshold values (i.e., <1mg Se/kg) under any scenario we evaluated. This analysis can assist the sampling design and interpretation of Se assessments from fish tissue by accounting for natural variation in stream fish populations.
|Original language||English (US)|
|Number of pages||7|
|Journal||Integrated Environmental Assessment and Management|
|State||Published - Jan 2015|
All Science Journal Classification (ASJC) codes
- Geography, Planning and Development
- Environmental Science(all)