PDF Print E-mail

 

 

  • Title of the thesis: Exploring the Bayesian hierarchical approach for the statistical modeling of spatial structures. Application in population ecology.

 

  • Defended on July 1, 2008 at the French institute AgroParisTech
  • Doctoral school: ABIES (for Agriculture, Food, Biology, Environment and Health)
  • Research team: Modelling and Risk Management in Environmental Science (MORSE) at the Joint Research department AgroParisTech/INRA "Applied Mathematics and Informatics". This research team is interested in statistical modelling and risk assessment/management in environmental science.

 

 

  • Referees: Verena Trenkel (IFREMER, Department "Ecologie et Modèles pour l'Halieutique", Nantes France) 
    Joël Chadoeuf (INRA, Unity Biostatistics and Spatial Processes)

    Commitee: Gilles Celeux (President, INRIA)
    Eric Parent (Supervisor)
    Gilles Guillot  (Co-supervisor)                              
    Marie-Pierre Etienne (Co-supervisor)
    Joël Chadoeuf (Referee)
    Verena Trenkel (Referee)
    Hugues Benoît (Examinator, Fisheries and Oceans Canada
    Avner Bar-Hen (Examinator, University Paris V)



 

 


 

 

 

 

 

  • Summary of the thesis:

    For most ecological questions, the random processes studied are spatially structured and come from the combined effect of several observed or unobserved random variables interacting at various scales. In practice, when data can't be directly treated with traditional spatial structures, observations are often considered as independent. Moreover, the usual models are often based on hypotheses that are too simple with regards to the complexity of the studied phenomena. In the present work, the hierarchical modelling framework is combined with some spatial statistics tools to build specific functional random structures for complex and spatially structured phenomena in population ecology. Model inference is done under the bayesian framework using MCMC algorithms. In the first part, a spatial hierarchical model (called Geneclust) is developed to identify genetically homogeneous populations when genetic diversity varies continuously in space. A hidden Markov random field, used to model the spatial structure of genetic diversity, is combined with a bivariate model for the occurrence of genotypes to take into account the possible occurrence of inbreeding in some natural populations. In the second part of the thesis, a particular compound Poisson process, called law of leaks, is presented from the hierarchical point of view. The goal was to describe the process of sampling living organisms. This approach explicitly confronts the technical issue of modelling continuous zero-inflated data from sampling characterized many zero values and variable sampling effort. This model is combined with different area-based models to add spatial dependencies between geographical units then with a bivariate gaussian random field built by process convolutions to model the joint spatial distribution of two species. The fitting and predictive capacities of the different hierarchical models are compared to the traditional models from simulated and real data (Scandinavian brown bears, epibenthic invertebrates in Saint-Lawrence Gulf (Canada)).


Keywords: MCMC algorithms, hidden Markov random fields, bivariate gaussian
random fields, multilocus genotype data, zero-inflated data, law of leaks,
hierarchical modelling, delta models, compound Poisson process, latent variables.

 

Statistical methods applied to: fisheries, population genetics




Last Updated on Tuesday, 24 January 2017 15:10