No abstract

Multivariate analyses are used widely for determining patterns of assemblage structure, inferring species-environment relationships and assessing human impacts on ecosystems. The estimation of ecological patterns often depends on sampling effort, so the degree to which sampling effort affects the outcome of multivariate analyses is a concern. We examined the effect of sampling effort on site and group separation, which was measured using a mean similarity method. Two similarity measures, the Jaccard Coefficient and Bray-Curtis Index were investigated with 1 benthic macroinvertebrate and 2 fish data sets. Site separation was significantly improved with increased sampling effort because the similarity between replicate samples of a site increased more rapidly than between sites. Similarly, the faster increase in similarity between sites of the same group than between sites of different groups caused clearer separation between groups. The strength of site and group separation completely stabilized only when the mean similarity between replicates reached 1. These results are applicable to commonly used multivariate techniques such as cluster analysis and ordination because these multivariate techniques start with a similarity matrix. Completely stable outcomes of multivariate analyses are not feasible. Instead, we suggest 2 criteria for estimating the stability of multivariate analyses of assemblage data: 1) mean within-site similarity across all sites compared, indicating sample representativeness, and 2) the SD of within-site similarity across sites, measuring sample comparability.

The electrofishing distance needed to estimate fish species richness at the stream or river reach scale is an important question in fisheries science. This distance is governed by the shape of the species accumulation curve, which, in turn, is influenced by a combination of factors, including the number of species, their overall abundances, habitat associations, the efficiency of the sampling method, and the occurrence of rare species. In this study we document the influence of rare species on the species accumulation curves from stream and river sites in data sets from five dispersed regions of the USA. Spatial discontinuity (i.e., a noncontinuous distribution within reaches) was observed in four of the five data sets, and the four data sets contained numerically rare species represented by one or two individuals (termed singletons and doubletons, respectively). Numerically rare species were typically proportionately rare (i.e., ,1% of the total number of individuals captured), but proportionately rare species were not always numerically rare and were dependent on the total number of fish captured. Species richness asymptotes were reached at shorter electrofishing distances when singletons and doubletons were removed. The number of singletons and doubletons in the samples remained relatively constant with increasing sampling effort (i.e., sampling distance and total abundance). Simulation modeling indicated that individual aggregation within species was not a plausible reason for spatially discontinuous species distributions. When accurately detecting the presence of species is a sampling goal, the presence and prevalence of numerically rare species may need to be considered in determining sampling protocols.

No abstract