Bayesian model selection for spatial capture–recapture models
Abstract A vast amount of ecological knowledge generated over the past two decades has hinged upon the ability of model selection methods to discriminate among various ecological hypotheses. The last decade has seen the rise of Bayesian hierarchical models in ecology. Consequently, commonly used too...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-10-01
|
| Series: | Ecology and Evolution |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/ece3.5551 |
| _version_ | 1818719981958856704 |
|---|---|
| author | Soumen Dey Mohan Delampady Arjun M. Gopalaswamy |
| author_facet | Soumen Dey Mohan Delampady Arjun M. Gopalaswamy |
| author_sort | Soumen Dey |
| collection | DOAJ |
| description | Abstract A vast amount of ecological knowledge generated over the past two decades has hinged upon the ability of model selection methods to discriminate among various ecological hypotheses. The last decade has seen the rise of Bayesian hierarchical models in ecology. Consequently, commonly used tools, such as the AIC, become largely inapplicable and there appears to be no consensus about a particular model selection tool that can be universally applied. We focus on a specific class of competing Bayesian spatial capture–recapture (SCR) models and apply and evaluate some of the recommended Bayesian model selection tools: (1) Bayes Factor—using (a) Gelfand‐Dey and (b) harmonic mean methods, (2) Deviance Information Criterion (DIC), (3) Watanabe‐Akaike's Information Criterion (WAIC) and (4) posterior predictive loss criterion. In all, we evaluate 25 variants of model selection tools in our study. We evaluate these model selection tools from the standpoint of selecting the “true” model and parameter estimation. In all, we generate 120 simulated data sets using the true model and assess the frequency with which the true model is selected and how well the tool estimates N (population size), a parameter of much importance to ecologists. We find that when information content is low in the data, no particular model selection tool can be recommended to help realize, simultaneously, both the goals of model selection and parameter estimation. But, in general (when we consider both the objectives together), we recommend the use of our application of the Bayes Factor (Gelfand‐Dey with MAP approximation) for Bayesian SCR models. Our study highlights the point that although new model selection tools are emerging (e.g., WAIC) in the applied statistics literature, those tools based on sound theory even under approximation may still perform much better. |
| first_indexed | 2024-12-17T20:15:35Z |
| format | Article |
| id | doaj.art-3e7f4539a5914527857c447ee04f2840 |
| institution | Directory Open Access Journal |
| issn | 2045-7758 |
| language | English |
| last_indexed | 2024-12-17T20:15:35Z |
| publishDate | 2019-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | Ecology and Evolution |
| spelling | doaj.art-3e7f4539a5914527857c447ee04f28402022-12-21T21:34:07ZengWileyEcology and Evolution2045-77582019-10-01920115691158310.1002/ece3.5551Bayesian model selection for spatial capture–recapture modelsSoumen Dey0Mohan Delampady1Arjun M. Gopalaswamy2Statistics and Mathematics Unit Indian Statistical Institute Bangalore IndiaStatistics and Mathematics Unit Indian Statistical Institute Bangalore IndiaStatistics and Mathematics Unit Indian Statistical Institute Bangalore IndiaAbstract A vast amount of ecological knowledge generated over the past two decades has hinged upon the ability of model selection methods to discriminate among various ecological hypotheses. The last decade has seen the rise of Bayesian hierarchical models in ecology. Consequently, commonly used tools, such as the AIC, become largely inapplicable and there appears to be no consensus about a particular model selection tool that can be universally applied. We focus on a specific class of competing Bayesian spatial capture–recapture (SCR) models and apply and evaluate some of the recommended Bayesian model selection tools: (1) Bayes Factor—using (a) Gelfand‐Dey and (b) harmonic mean methods, (2) Deviance Information Criterion (DIC), (3) Watanabe‐Akaike's Information Criterion (WAIC) and (4) posterior predictive loss criterion. In all, we evaluate 25 variants of model selection tools in our study. We evaluate these model selection tools from the standpoint of selecting the “true” model and parameter estimation. In all, we generate 120 simulated data sets using the true model and assess the frequency with which the true model is selected and how well the tool estimates N (population size), a parameter of much importance to ecologists. We find that when information content is low in the data, no particular model selection tool can be recommended to help realize, simultaneously, both the goals of model selection and parameter estimation. But, in general (when we consider both the objectives together), we recommend the use of our application of the Bayes Factor (Gelfand‐Dey with MAP approximation) for Bayesian SCR models. Our study highlights the point that although new model selection tools are emerging (e.g., WAIC) in the applied statistics literature, those tools based on sound theory even under approximation may still perform much better.https://doi.org/10.1002/ece3.5551Bayes factorsBayesian inferenceDIChierarchical modelsposterior predictive lossWAIC |
| spellingShingle | Soumen Dey Mohan Delampady Arjun M. Gopalaswamy Bayesian model selection for spatial capture–recapture models Ecology and Evolution Bayes factors Bayesian inference DIC hierarchical models posterior predictive loss WAIC |
| title | Bayesian model selection for spatial capture–recapture models |
| title_full | Bayesian model selection for spatial capture–recapture models |
| title_fullStr | Bayesian model selection for spatial capture–recapture models |
| title_full_unstemmed | Bayesian model selection for spatial capture–recapture models |
| title_short | Bayesian model selection for spatial capture–recapture models |
| title_sort | bayesian model selection for spatial capture recapture models |
| topic | Bayes factors Bayesian inference DIC hierarchical models posterior predictive loss WAIC |
| url | https://doi.org/10.1002/ece3.5551 |
| work_keys_str_mv | AT soumendey bayesianmodelselectionforspatialcapturerecapturemodels AT mohandelampady bayesianmodelselectionforspatialcapturerecapturemodels AT arjunmgopalaswamy bayesianmodelselectionforspatialcapturerecapturemodels |