Assessing the impacts of grazing levels on bird density in woodland habitat: a Bayesian approach using expert opinion

摘要: Many studies on birds focus the collection of data through an experimental design, suitable for investigation in a classical analysis variance (ANOVA) framework. Although many findings are confirmed by one or more experts, expert information is rarely used conjunction with survey to enhance explanatory and predictive power model. We explore this neglected aspect ecological modelling study Australian woodland birds, focusing potential impact different intensities commercial cattle grazing bird density habitat. examine number Bayesian hierarchical random effects models, which cater overdispersion high frequency zeros using WinBUGS variation between within regimes species. The value investigated inclusion priors that reflect experience 20 experts field responses disturbance. Results indicate moderates data, especially situations where there little no data. When agreed, credible intervals predictions were tightened considerably. failed agree, results similar those evaluated absence information. Overall, we found without opinion our knowledge was quite weak. fact consistent, general, shows do know something about could learn lot faster if approach ecology, scarce. Copyright (c) 2005 John Wiley & Sons, Ltd.