The various debates around model selection paradigms are important, but in lieu of a consensus, there is a demonstrable need for a deeper appreciation of existing approaches, at least among the end-users of statistics and model selection tools. In the ecological literature, the Akaike information criterion (AIC) dominates model selection practices, and while it is a relatively straightforward concept, there exists what we perceive to be some common misunderstandings around its application. Two specific questions arise with surprising regularity among colleagues and students when interpreting and reporting AIC model tables. The first is related to the issue of ‘pretending’ variables, and specifically a muddled understanding of what this means. The second is related to p -values and what constitutes statistical support when using AIC. There exists a wealth of technical literature describing AIC and the relationship between p -values and AIC differences. Here, we complement this technical treatment and use simulation to develop some intuition around these important concepts. In doing so we aim to promote better statistical practices when it comes to using, interpreting and reporting models selected when using AIC.

Environmental DNA (eDNA) metabarcoding has revolutionized biomonitoring in both marine and freshwater ecosystems. However, for semi‐aquatic and terrestrial animals, the application of this technique remains relatively untested. We first assess the efficiency of eDNA metabarcoding in detecting semi‐aquatic and terrestrial mammals in natural lotic ecosystems in the UK by comparing sequence data recovered from water and sediment samples to the mammalian communities expected from historical data. Secondly, using occupancy modelling we compared the detection efficiency of eDNA metabarcoding to multiple conventional non‐invasive survey methods (latrine surveys and camera trapping). eDNA metabarcoding detected a large proportion of the expected mammalian community within each area. Common species in the areas were detected at the majority of sites. Several key species of conservation concern in the UK were detected by eDNA sampling in areas where authenticated records do not currently exist, but potential false positives were also identified. Water‐based eDNA metabarcoding provided comparable results to conventional survey methods in per unit of survey effort for three species (water vole, field vole and red deer) using occupancy models. The comparison between survey ‘effort’ to reach a detection probability of ≥.95 revealed that 3–6 water replicates would be equivalent to 3–5 latrine surveys and 5–30 weeks of single camera deployment, depending on the species. Synthesis and applications. eDNA metabarcoding can be used to generate an initial ‘distribution map’ of mammalian diversity at the landscape level. If conducted during times of peak abundance, carefully chosen sampling points along multiple river courses provide a reliable snapshot of the species that are present in a catchment area. In order to fully capture solitary, rare and invasive species, we would currently recommend the use of eDNA metabarcoding alongside other non‐invasive surveying methods (i.e. camera traps) to maximize monitoring efforts.