Estimating harvest when hunting bag data are reported by area rather than individual hunters: A Bayesian autoregressive approach

Harvest estimation is a central part of adaptive management wildlife. In the absence complete reporting, statishods are required to extrapolate from available data. We developed Hierarchical Bayesian framework tailored for partial reporting where hunting areas covered by teams available. The accounts autocorrelation at national, county, and precinct levels. derived evaluated an approximation probability harvest on non-reported under non-linear relationship between area per team rate. applied reports red fox (Vulpes vulpes), wild boar (Sus scrofa), common eider (Somateria mollissima), grey partridge (Perdix perdix) in Sweden years 1997/1998–2019/2020. was determined be sufficiently accurate. showed that accounting reduced uncertainty increased predictive accuracy, particularly game hunted low numbers variably teams. analysis also revealed rate has sub-linear with team’s all considered species. Further, substantial differences across regions terms parameters modeling distribution huntable land as well rates. conclude useful detect shifts rates and/or practices.