Facebook Icon Twitter Icon Youtube Icon Linked Icon Git Icon

Accepting Applications: Bayesian Modeling for Socio-Environmental Data

Printer-friendly versionPDF version
Feb 28, 2017

Solutions to pressing environmental problems require understanding connections between human and natural systems. Analysis of these systems requires models that can deal with complexity, are able to exploit data from multiple sources, and are honest about uncertainty that arises in different ways. Synthesis of results from multiple studies is often required. Bayesian hierarchal models provide a powerful approach to analysis of socio-environmental problems that are complex and that require synthesis of knowledge.

Past participants of this short course have worked on research questions including, but not limited to, the use of network analyses to understand measurement uncertainly in the context of extreme weather events, the study of governance effectiveness and fisheries biomass, and the relationship between advocacy group compositions and estuarine quality.

The National Socio-Environmental Synthesis Center (SESYNC) will host a nine-day short course August 15 - 25, 2017 covering basic principles of using Bayesian models to gain insight from data. The goals of the course are to:

  1. Provide a principles-based understanding of Bayesian methods needed to train students, evaluate papers and proposals, and solve research problems.
  2. Communicate the statistical concepts and vocabulary needed to foster collaboration between ecologists, social scientists, and statisticians.
  3. Provide the conceptual foundations and quantitative confidence needed for self-teaching modern analytical methods.

The course will enable participants to:

  1. Explain key principles of Bayesian statistics, including the concepts of joint, conditional, and marginal probabilities; posterior and prior distributions; likelihood; conjugacy; conditioning; and the relationship among simple Bayesian, hierarchical Bayesian, and maximum likelihood methods.
  2. Use basic statistical distributions (e.g., binomial, Poisson, normal, lognormal, multinomial, beta, Dirichlet, gamma) to write joint and conditional posterior distributions for hierarchical Bayesian models that couple models of ecological processes, models of data, and random effects.
  3. Explain how Markov chain Monte Carlo (MCMC) methods can be used to estimate the posterior distributions of parameters.
  4. Write algorithms and computer code in R implementing MCMC methods to estimate parameters in simple models.
  5. Use JAGS software to implement MCMC methods for estimating posterior distributions of parameters, latent states, and derived quantities.
  6. Evaluate model convergence and assess goodness of fit of models to data.
  7. Develop and implement hierarchical models that explicitly partition uncertainties.
  8. Understand the basis for statistical inference from single and multiple Bayesian models.
  9. Use Bayesian methods to synthesize results from multiple scientific studies.

Short Course Format

The course will include lectures and laboratory exercises. Labs will emphasize problem solving requiring programming in R and JAGS. There will be 4–6 group projects using data provided by participants. The projects will be aimed at producing published manuscripts.

Short Course Details

  • The course will be held August 15–25, 2017 at SESYNC in Annapolis, Maryland, and will meet daily from 9 a.m.–5 p.m.
    There will be no meeting on Sunday, August 20.
  • The course is aimed at postdoc, researcher, and faculty participants. Grad students may also be considered.
  • There is no fee to attend, but participants are responsible for most of their own travel and accommodations.
  • For those willing to share a room with another participant, SESYNC will provide local hotel accommodations. If a private hotel room is desired, SESYNC will cover 50% of hotel costs.
  • Coffee/tea and lunch will be provided daily.

Application Details

  • Complete the webform here, including your CV, a description of your research interests and background in mathematics and statistics, and a paragraph describing how you might extend what you learn in this course to a broader community, no later than May 26, 2017, at 5 p.m. Eastern Time (ET).
  • Selected participants will be notified by June 16, 2017.
  • The course will be limited to 25 participants.
  • All participants must be proficient users of R and be able to bring a laptop to each class meeting.

Instructor Bios

Dr. Tom Hobbs has taught ecological modeling at Colorado State University for 14 years. His course has evolved over time; during the last six years, it has emphasized likelihood-based and Bayesian methods for model-data assimilation. He has also taught short courses for the U.S. Geological Survey, the Grimso Wildlife Research Institute, and the Department of Ecology, Swedish Agricultural University. He currently leads an annual workshop for postdocs, agency researchers, and faculty sponsored by the National Science Foundation. He is the author, with Mevin Hooten, of Bayesian models: A statistical primer for ecologists from Princeton University Press. Hobbs takes special pride in making challenging, quantitative concepts clear and accessible to students who never considered themselves to be particularly adept with mathematics and statistics.

Dr. Mary Collins is an environmental sociologist and Assistant Professor at the College of Environmental Science and Forestry at the State University of New York. Dr. Collins is also a former postdoctoral fellow SESYNC where she used large datasets to study the spatial distribution of environmental inequality and related issues of justice in the United States. Although well-versed in frequentist approaches, she is a relative newcomer to Bayesian modeling. Originally a student in one of Hobbs’ earlier workshops, at this short course she will help to both translate concepts across disciplinary boundaries and demonstrate how focused study and scholarly support can lead to the development of a new analytic skill set.

Dr. Christian Che-Castaldo is an ecologist and postdoctoral research associate with Dr. William Fagan at the University of Maryland. He uses observational and experimental field studies, in conjunction with occupancy and demographic modeling, to better understand how host plant sex and stress affect plant–herbivore dynamics, as well as the cause and maintenance of sex ratio bias in willow. Chris was a participant in one of Hobbs’ earlier workshops, and also served as an external reviewer for Hobbs and Hooten's upcoming book, Bayesian models: A statistical primer for ecologists. He enjoys helping others learn statistics by working to apply Bayesian modeling methods to their own research questions.


Please email Dr. Mary Collins at: mbcollin@esf.edu

Associated SESYNC Researcher(s):