The importance of survey design in distance sampling: field evaluation using domestic sheep

Context Sampling methods to estimate animal density require good survey design to ensure assumptions are met and sampling is representative of the survey area. Management decisions are often made based on these estimates. However, without knowledge of true population size it is not possible for wildlife biologists to evaluate how biased the estimates can be if survey design is compromised. Aims Our aims were to use distance sampling to estimate population size for domestic sheep free-ranging within large enclosed areas of hill country and, by comparing estimates against actual numbers, examine how bias and precision are impaired when survey design is compromised. Methods We used both line and point transect sampling to derive estimates of density for sheep on four farms in upland England. In Stage I we used limited effort and different transect types to compromise survey design. In Stage II we increased effort in an attempt to improve on the Stage I estimates. We also examined the influence of a walking observer on sheep behaviour to assess compliance with distance sampling assumptions and to improve the fit of models to the data. Key results Our results show that distance sampling can lead to biased and imprecise density estimates if survey design is poor, particularly when sampling high density and mobile species that respond to observer presence. In Stage I, walked line transects were least biased; point transects were most biased. Increased effort in Stage II reduced the bias in walked line transect estimates. For all estimates, the actual density was within the derived 95% confidence intervals, but some of these spanned a range of over 100 sheep per km2. Conclusions Using a population of known size, we showed that survey design is vitally important in achieving unbiased and precise density estimation using distance sampling. Adequate transect replication reduced the bias considerably within a compromised survey design. Implications Management decisions based on poorly designed surveys must be made with an appropriate understanding of estimate uncertainty. Failure to do this may lead to ineffective management.