Bayesian Clustering of Animal Abundance Trends for Inference and Dimension Reduction

We consider a model-based clustering approach to examining abundance trends in a metapopulation. When examining trends for an animal population with management goals in mind one is often interested in those segments of the population that behave similarly to one another with respect to abundance. Our proposed trend analysis incorporates a clustering method that is an extension of the classic Chinese Restaurant Process, and the associated Dirichlet process prior, which allows for inclusion of distance covariates between sites. This approach has two main benefits: (1) nonparametric spatial association of trends and (2) reduced dimension of the spatio-temporal trend process. We present a transdimensional Gibbs sampler for making Bayesian inference that is efficient in the sense that all of the full conditionals can be directly sampled from save one. To demonstrate the proposed method we examine long term trends in northern fur seal pup production at 19 rookeries in the Pribilof Islands, Alaska. There was strong evidence that clustering of similar year-to-year deviation from linear trends was associated with whether rookeries were located on the same island. Clustering of local linear trends did not seem to be strongly associated with any of the distance covariates. In the fur seal trends analysis an overwhelming proportion of the MCMC iterations produced a 73–79 % reduction in the dimension of the spatio-temporal trend process, depending on the number of cluster groups.

[1]  J. Pitman.  Combinatorial Stochastic Processes , 2006 .

[2]  R. Towell,et al.  DECLINE IN NORTHERN FUR SEAL (CALLORHINUS URSINUS) PUP PRODUCTION ON THE PRIBILOF ISLANDS , 2006 .

[3]  Peter I. Frazier,et al.  Distance dependent Chinese restaurant processes , 2009, ICML.

[4]  D. G. Chapman,et al.  Estimation of Fur Seal Pup Populations by Randomized Sampling , 1968 .

[5]  Elizabeth E. Holmes,et al.  Inferring spatial structure from time‐series data: using multivariate state‐space models to detect metapopulation structure of California sea lions in the Gulf of California, Mexico , 2010 .

[6]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[7]  R. Dorazio.  On selecting a prior for the precision parameter of Dirichlet process mixture models , 2009 .

[8]  S. MacEachern,et al.  Estimating mixture of dirichlet process models , 1998 .

[9]  Mevin B. Hooten,et al.  An Accessible Method for Implementing Hierarchical Models with Spatio-Temporal Abundance Data , 2012, PloS one.

[10]  M. Stein.  Space–Time Covariance Functions , 2005 .

[11]  T. Ferguson.  A Bayesian Analysis of Some Nonparametric Problems , 1973 .

[12]  Li Zhang,et al.  Modeling Unobserved Sources of Heterogeneity in Animal Abundance Using a Dirichlet Process Prior , 2008, Biometrics.

[13]  M. Escobar,et al.  Bayesian Density Estimation and Inference Using Mixtures , 1995 .

[14]  R. Ream,et al.  Foraging habitats based on the diet of female northern fur seals (Callorhinus ursinus) on the Pribilof Islands, Alaska , 2006 .

[15]  Susan A. Murphy,et al.  Monographs on statistics and applied probability , 1990 .

[16]  Roger L. Gentry,et al.  Northern Fur Seal Behavior and Ecology@@@Behavior and Ecology of the Northern fur Seal , 1998 .

[17]  Radford M. Neal.  Markov Chain Sampling Methods for Dirichlet Process Mixture Models , 2000 .

[18]  Jeremy T. Sterling,et al.  Foraging route tactics and site fidelity of adult female northern fur seal (Callorhinus ursinus) around the Pribilof Islands , 2008 .

[19]  Fernando A. Quintana,et al.  Nonparametric Bayesian data analysis , 2004 .

[20]  Leonhard Held,et al.  Gaussian Markov Random Fields: Theory and Applications , 2005 .

[21]  Jennifer A. Hoeting,et al.  Bayesian Multimodel Inference for Geostatistical Regression Models , 2011, PloS one.