A novel field evaluation of the effectiveness of distance and independent observer sampling to estimate aural avian detection probabilities

Summary 1. The validation of field sampling techniques is a concern for applied ecologists due to the strong model assumptions implicit in all methods. Computer simulations make replication easy, but they do not give insights into how much bias occurs in real populations. Testing sampling methods on populations of known size can establish directly how well estimators perform, but such populations are very hard to find, and replicate, and they may have unusual attributes. 2. We present a field validation of distance and double-observer methods of estimating detection probabilities on aural avian point counts. Our research is relevant to conservation agencies worldwide who design thousands of avian monitoring programmes based primarily on auditory point counts. The programmes are a critical component in the management of many avian species. 3. Our validation used a simulation system which mimics birds calling in a field environment. The system allowed us to vary singing rate, species, distance, the complexity of points, and other factors. 4. Distance methods performed poorly, primarily due to large localization errors, and estimates did not improve for simplified points. 5. For the double-observer method, two pairs of observers tended to underestimate true population size, while the third pair tended to double-count birds which overestimated the population. Detection probabilities were always higher and population estimates lower when observers subjectively matched birds compared to an objective rule and showed a slight negative bias and good precision. A simplified 45-degree matching rule did not improve the performance of double-observer estimates which had a slight positive bias and much lower precision. Double-observer estimates did improve on the simplified points. 6. Synthesis and applications . We encourage ecologists working with sampling methods to develop similar methods of working with simulated populations through use of technology. Our simulated field evaluation has demonstrated the difficulty of accurately estimating population size when limited to aural detections. Problems are related to limitations in the ability of observers to localize sound, estimate distance, and accurately identify birds during a count. Other sources of error identified are the effects of observers, singing rate, singing orientation and background noise.