Improving occupancy estimation when two types of observational error occur: non‐detection and species misidentification

摘要: Efforts to draw inferences about species occurrence frequently account for false negatives, the common situation when individuals of a are not detected even site is occupied. However, recent studies suggest need also deal with positives, which occur misidentified so that recorded as unoccupied. Bias in estimators occupancy, colonization, and extinction can be severe positives occur. Accordingly, we propose models simultaneously both types error. Our approach used improve estimates occupancy study designs where subset detections type or method assumed We illustrate properties simulations data three frogs. show possible misidentification have greater support (lower AIC two species) yield substantially different than those do not. When potential exists, researchers should consider analytical techniques this source error, such presented here.