A spatial-temporal double-hurdle model for extremely over-dispersed avian count data

详细信息    查看全文

• 作者：Earvin Balderama^a ; ^{ebalderama@luc.edu} ; Beth Gardner^b ; ^bg43@uw.edu ; Brian J. Reich^c ; ^{bjreich@ncsu.edu}
• 关键词：Bayesian hierarchical modeling ; Conditional autoregressive models ; Extreme values ; Generalized Pareto distribution ; Seabirds ; Zero-inflation
• 刊名：Spatial Statistics
• 出版年：2016
• 出版时间：November 2016
• 年：2016
• 卷：18
• 期：part_PA
• 页码：263-275
• 全文大小：1164 K
• 卷排序：18

文摘

Several wind energy facilities are currently being planned for offshore Atlantic waters of the United States. However, relatively little is known about the distribution, abundance and spatio-temporal variability of marine birds in their offshore habitats and it is becoming increasingly necessary to accurately characterize these demographic parameters before assessing the influence of factors such as offshore energy development on populations. Thus, we incorporate a multi-scale approach to develop models for the space-time distribution and abundance of marine birds to identify potential high-use areas in need of further study. With data taken from past and ongoing survey efforts, we provide relative abundance and density estimates for marine birds over a wide geographical area during multiple years. Due to the excessive amount of zeros as well as extremely large counts exhibited in the data, a double-hurdle model is formulated that includes a negative binomial and a generalized Pareto distribution mixture. Spatial heterogeneity is modeled using a conditional auto-regressive (CAR) prior, and a Fourier basis was used for seasonal variation. We demonstrate our model by creating probability maps that show areas of high-abundance and aggregation for twenty-four species of marine bird.