More Like this

1. Quantifying Community Resilience Using Hierarchical Bayesian Kernel Methods: A Case Study on Recovery from Power Outages

   https://doi.org/10.1111/risa.13343  

   Yu, Jin‐Zhu; Baroud, Hiba (July 2019, Risk Analysis)

   Abstract The ability to accurately measure recovery rate of infrastructure systems and communities impacted by disasters is vital to ensure effective response and resource allocation before, during, and after a disruption. However, a challenge in quantifying such measures resides in the lack of data as community recovery information is seldom recorded. To provide accurate community recovery measures, a hierarchical Bayesian kernel model (HBKM) is developed to predict the recovery rate of communities experiencing power outages during storms. The performance of the proposed method is evaluated using cross‐validation and compared with two models, the hierarchical Bayesian regression model and the Poisson generalized linear model. A case study focusing on the recovery of communities in Shelby County, Tennessee after severe storms between 2007 and 2017 is presented to illustrate the proposed approach. The predictive accuracy of the models is evaluated using the log‐likelihood and root mean squared error. The HBKM yields on average the highest out‐of‐sample predictive accuracy. This approach can help assess the recoverability of a community when data are scarce and inform decision making in the aftermath of a disaster. An illustrative example is presented demonstrating how accurate measures of community resilience can help reduce the cost of infrastructure restoration. 

   more » « less
2. Bayesian Model Selection for Generalized Linear Mixed Models

   https://doi.org/10.1111/biom.13896  

   Xu, Shuangshuang; Ferreira, Marco_A_R; Porter, Erica_M; Franck, Christopher_T (June 2023, Biometrics)

   Abstract We propose a Bayesian model selection approach for generalized linear mixed models (GLMMs). We consider covariance structures for the random effects that are widely used in areas such as longitudinal studies, genome-wide association studies, and spatial statistics. Since the random effects cannot be integrated out of GLMMs analytically, we approximate the integrated likelihood function using a pseudo-likelihood approach. Our Bayesian approach assumes a flat prior for the fixed effects and includes both approximate reference prior and half-Cauchy prior choices for the variances of random effects. Since the flat prior on the fixed effects is improper, we develop a fractional Bayes factor approach to obtain posterior probabilities of the several competing models. Simulation studies with Poisson GLMMs with spatial random effects and overdispersion random effects show that our approach performs favorably when compared to widely used competing Bayesian methods including deviance information criterion and Watanabe–Akaike information criterion. We illustrate the usefulness and flexibility of our approach with three case studies including a Poisson longitudinal model, a Poisson spatial model, and a logistic mixed model. Our proposed approach is implemented in the R package GLMMselect that is available on CRAN. 

   more » « less
3. Generalized fiducial inference on the mean of zero-inflated Poisson and Poisson hurdle models

   https://doi.org/10.1186/s40488-021-00117-0  

   Zou, Yixuan; Hannig, Jan; Young, Derek S. (December 2021, Journal of Statistical Distributions and Applications)

   null (Ed.)

   Abstract Zero-inflated and hurdle models are widely applied to count data possessing excess zeros, where they can simultaneously model the process from how the zeros were generated and potentially help mitigate the effects of overdispersion relative to the assumed count distribution. Which model to use depends on how the zeros are generated: zero-inflated models add an additional probability mass on zero, while hurdle models are two-part models comprised of a degenerate distribution for the zeros and a zero-truncated distribution. Developing confidence intervals for such models is challenging since no closed-form function is available to calculate the mean. In this study, generalized fiducial inference is used to construct confidence intervals for the means of zero-inflated Poisson and Poisson hurdle models. The proposed methods are assessed by an intensive simulation study. An illustrative example demonstrates the inference methods. 

   more » « less
4. Energy Distribution Modeling for Assessment and Optimal Distribution of Sustainable Energy for On-Grid Food, Energy, and Water Systems in Remote Microgrids

   https://doi.org/10.3390/su13179511  

   Chamberlin, Michele J.; Sambor, Daniel J.; Karenzi, Justus; Wies, Richard; Whitney, Erin (September 2021, Sustainability)

   null (Ed.)

   Food, energy, and water (FEW) are essential for human health and economic development. FEW systems are inextricably interlinked, yet individualized and variable. Consequently, an accurate assessment must include all available and proposed FEW components and their interconnections and consider scale, location, and scope. Remote Alaska locations are examples of isolated communities with limited infrastructure, accessibility, and extreme climate conditions. The resulting challenges for FEW reliability and sustainability create opportunities to obtain practical insights that may apply to other remote communities facing similar challenges. By creating energy distribution models (EDMs), a methodology is proposed, and a tool is developed to measure the impacts of renewable energy (RE) on small FEW systems connected to the microgrids of several Alaska communities. Observing the community FEW systems through an energy lens, three indices are used to measure FEW security: Energy–Water (EW), Energy–Food (EF), and Sustainable Energy (SE). The results indicate the impacts of RE on FEW infrastructure systems are highly seasonal, primarily because of the natural intermittence and seasonality of renewable resources. Overall, there is a large potential for RE integration to increase FEW security as well as a need for additional analysis and methods to further improve the resiliency of FEW systems in remote communities. 

   more » « less
5. Synthesis of recovery patterns in microbial communities across environments

   https://doi.org/10.1186/s40168-024-01802-3  

   Jurburg, Stephanie D; Blowes, Shane A; Shade, Ashley; Eisenhauer, Nico; Chase, Jonathan M (December 2024, Microbiome)

   Abstract BackgroundDisturbances alter the diversity and composition of microbial communities. Yet a generalized empirical assessment of microbiome responses to disturbance across different environments is needed to understand the factors driving microbiome recovery, and the role of the environment in driving these patterns. ResultsTo this end, we combined null models with Bayesian generalized linear models to examine 86 time series of disturbed mammalian, aquatic, and soil microbiomes up to 50 days following disturbance. Overall, disturbances had the strongest effect on mammalian microbiomes, which lost taxa and later recovered their richness, but not their composition. In contrast, following disturbance, aquatic microbiomes tended away from their pre-disturbance composition over time. Surprisingly, across all environments, we found no evidence of increased compositional dispersion (i.e., variance) following disturbance, in contrast to the expectations of the Anna Karenina Principle. ConclusionsThis is the first study to systematically compare secondary successional dynamics across disturbed microbiomes, using a consistent temporal scale and modeling approach. Our findings show that the recovery of microbiomes is environment-specific, and helps to reconcile existing, environment-specific research into a unified perspective. 

   more » « less