Développer des collaborations est, me semble-t-il, une étape nécessaire et cruciale pour élaborer des projets, favoriser des recherches innovantes, pérenniser des systèmes de formation et obtenir les financements nécessaires. Au niveau national, les collaborations que j’ai pu développer avec l’univer-sité de Montpellier, avec l’INRA d’Avignon ou de Bordeaux, avec les membres de l’équipe MORSE d’AgroParisTech, avec l’université Lille I ainsi qu’avec le groupe » Statistiques pour l’environnement » de la Société Française de la Statistique ou encore le groupe de recherche (GDR) dédié à l’écologie sta-tistique me permet de promouvoir les stasta-tistiques pour une gestion durable des forêts tropicales. L’existence de ce réseau devrait favoriser l’émergence de projets de recherche et aider à trouver des appuis précieux pour promouvoir la formation des statistiques dans les pays du sud et en particulier dans les pays francophones du bassin du Congo.
semble donc nécessaire de les élargir, en particulier avec les États-Unis en m’appuyant sur la collaboration que j’ai établie depuis quelques années avec les Pr. Tadesse et A. Arab de Georgetown University. Cette coopération m’a offert l’opportunité, depuis 2013, d’être invité à présenter mes travaux d’une part dans quatre universités américaines différentes (en 2013 dans le département de mathématiques et statistiques de Georgetown University (M. Tadesse), en 2014 dans le département de statistiques de Rice University (M. Vanucci), en 2015 dans le département de statistiques de Georges Washington University (T. Apanasovich) et en 2015 dans le département d’entomologie de Madison-Wisconsin University (J. Zhu)) et d’autre part à trois conférences internationales (en 2014 et 2015 dans la conférence « Eastern North Ame-rica Region » et en 2015 à la réunion annuelle de l’« AmeAme-rican Mathematical Society »). De plus, cette collaboration a donné lieu à un premier projet fi-nancé par le « Georgetown Environmetal Initiaves » à hauteur de 17,000$. Celui-ci nous a permis d’encadrer deux étudiants de Master. Je m’efforce aussi depuis peu à mettre sur pied un groupe de recherche autour du thème « Common efforts for tropical forests ». Cette démarche pourrait alors aisé-ment rejoindre des projets américains ambitieux existants tel que le « Congo Basin Institute » qui visent aussi à promouvoir la formation et la recherche au sein des pays africains. En ce sens, je pense qu’il serait intéressant, pour moi, pour l’équipe et plus globalement pour le Cirad que je sois positionné, pour un temps, à Georgetown University.
Bibliographie
Akaike, H. (1974). A new look at the statistical model identification. IEEE
Transactions on Automatic Control, 19 :716–723. 35
Albert, J. and Chib, S. (1993). Bayesian analysis of binary and polychoto-mous response data. J. Amer. Statist. Assoc., 88 :669–679. 41
Atchade, Y. (2006). An adaptive version for the Metropolis Adjusted Lange-vin Algorithm with a truncated drift. Methodol. Comput. Appl. Probab., 8 :235–254. 43
Atchade, Y. F. and Rosenthal, J. S. (2005). On adaptive Markov chain Monte Carlo algorithms. Bernoulli, 11 :815–828. 43
Baillargeon, S. (2005). Le krigeage : revue de la théorie et application à l’interpolation spatiale de données de précipitations. Mémoire de maîtrise, Université Laval, Québec. 32
Banerjee, S., Carlin, B., and Gelfand, A. (2004). Hierarchical modeling and analysis for spatial data, volume 101 of Monographs on Statistics & Applied Probability. Chapman & Hall/CRC, Boca Raton, FL. 31, 32, 46
Bar-Hen, A. and Mortier, F. (2004). Influence and sensitivity measures in correspondence analysis. Statistics, 38(3) :207–215. 41
Barbault, R. and Weber, J. (2010). La vie, quelle entreprise ! Seuil. 21 Barry, R. and Ver Hoef, J. (1996). Blackbox kriging : spatial prediction
without specifying variogram models. Journal of Agricultural, Biological,
and Environmental Statistics, 1 :297–322. 33
Bartholomé, J., Salmon, F., Vigneron, P., Bouvet, J., Plomion, C., and Gion, J. (2013). Plasticity of primary and secondary growth dynamics in euca-lyptus hybrids : A quantitative genetics and qtl mapping perspective. BMC Plant Biology, 13. 28
Bedel, F., Durrieu de Madron, L., Dupuy, B., Favrichon, V., Maître, H., Bar-Hen, A., and Narboni, P. (1998). Dynamique de croissance dans des peuplements exploités et éclaircis de forêt dense africaine. le dispositif de M’baïki en république centrafricaine (1982-1995). CIRAD Forêt,
Montpel-lier. Série FORAFRI, document, 1 :71. 22
Bellwood, D. and Wainwright, P. (2001). Locomotion in labrid fishes : impli-cations for habitat use and cross-shelf biogeography on the great barrier reef. Coral Reefs, 20 :139–150. 34
Besag, J. E. (1994). Discussion of paper by U. Grenander and M. I. Miller. Journal of Royal Statistical Society. Series B, 56 :591–592. 43
Biernacki, C., Celeux, G., and Govaert, G. (2000). Assessing a mixture model for clustering with the integratedcompleted likelihood. IEEE Transactions
on Pattern Analysis and Machine Intelligence, 22 :719–725. 35
Blaser, J., Sarre, A., and Poore, D. e. a. (2011). Status of tropical forest
management 2011. 21
Bliss, C. (1935). The calculation of dosage-mortality curve. Annals of Applied
Biology, 22 :307–330. 41
Breyer, L. A. and Roberts, G. O. (2000). From Metropolis to diffusions : Gibbs states and optimal scaling. Stochastic Processes and their Applica-tions, 90 :181–206. 43
Bry, X., Trottier, C., Mortier, F., Cornu, G., and Verron, T. (2015). Super-vised component generalised linear regression with multiple explanatory blocks : Theme-scglr. PLS 2014, 1 :1–10. , 39, 61, 64, 66, 69
Bry, X., Trottier, C., Verron, T., and Mortier, F. (2013). Supervised com-ponent generalized linear regression using a pls-extension of the fisher sco-ring algorithm. Journal of Multivariate Analysis, 119 :47 – 60. , 39, 61, 69
Caswell, H. (2001). Matrix population models : Construction, analysis and interpretation. Sinauer Associates, Inc. Publishers, Sunderland, Massachu-setts, second edition. 49
Ceccato, P., Bango, E., Ngouanze, F., , and Damio, T. (1992). étude pé-dologique des parcelles d’expérimentation des forêts de boukoko et la lolé (M’baïki) (république centrafricaine). 23
Chagneau, P., Mortier, F., and Picard, N. (2009). Designing permanent sample plots by using a spatially hierarchical matrix population model. Journal Of The Royal Statistical Society Series C, 58 :345–367. ,34, 40 Chagneau, P., Mortier, F., Picard, N., and Bacro, J. (2011). Prediction of
a multivariate spatial random field with continuous, count and ordinal outcomes. Biometrics, 58 :345–367. , 32, 34,40
Chaubert, F., Mortier, F., and André, L. (2008). Multivariate dynamic model for ordinal outcomes. Journal of Multivariate Analysis, 99 :1717–1732. 32, 42
Chelldorfer, J., Bühlmann, P., and van de Geer, S. (2011). Estimation for high-dimensional linear mixed-effects models using l1-penalization. Scan-dinavian Journal of Statistics, 38 :197–214. 60
Chen, M.-H. and Shao, Q.-M. (1999). Properties of prior and posterior dis-tributions for multivariate categorical response data models. Journal of Multivariate Analysis, 71 :277–296. 41
Chib, S. and Greenberg, E. (1998). Analysis of multivariate probit models.
Biometrika, 85 :347–361. 41
Christensen, O. and Waagepetersen, R. (2002). Bayesian prediction of spatial count data using Generalized Linear Mixed Models. Biometrics, 58 :280– 286. 32, 43
Christensen, O. F., Møller, J., and Waagepetersen, R. P. (2001). Geometric ergodicity of Metropolis-Hastings algorithms for conditional simulation in generalized linear mixed models. Methodology and Computing in Applied Probability, 3 :309–327. 43
Clark, J. (2005). Why environmental scientists are becoming bayesians. Eco-logy Letters, 8 :2–14. 29, 31
Cornu, G., Mortier, F., Trottier, C., and Bry, X. (2015). SCGLR : Supervised
Component Generalized Linear Regression. R package version 2.0.2. 39,
65
Cressie, N. (1991). Statistics for spatial Data. John Wiley & Sons. 32 Cressie, N., Caldery, C., Clark, J., Ver Hoef, J., and Wikle, C. (2009).
Accoun-ting for uncertainty in ecological analysis : the strengths and limitations of hierarchical statistical modeling. Agencies and staff of the US department of commerce. 30, 31
Daudin, J.-J., Picard, F., and Robin, S. (2008). A mixture model for random graphs. Statistics and Computing, 18 :151–171. 34
Dellaportas, P., Forster, J., and Ntzoufras, I. (2002). On bayesian model and variable selection using mcmc. Statistics and Computing, 12 :27–36. 47 Dellaportas, P., Forster, J. J., and Ntzoufras, I. (2000). Bayesian variable
selection using the gibbs sampler. 38
Diggle, P., Tawn, J., and Moyeed, R. (1998). Model-based geostatistics. (With discussion). Journal of Royal Statistical Society. Series C, 47 :299– 350. 32, 41
Dunstan, P., Foster, S., Hui, F., and Warton, D. (2013). Finite mixture of regression modeling for high-dimensional count and biomass data in ecology. Journal of Agricultural, Biological, and Environmental Statistics, 18 :357–375. 34, 35
Dunstan, P. K., Foster, S. D., and Darnell, R. (2011). Model based grouping of species accross environmental gradient. Ecological Modeling, 222 :955– 963. 34, 35
Eerikäinen, K., Miina, J., and Valkonen, S. (2007). Models for the regenera-tion establishment and the development of established seedlings in uneven-aged, norway spruce forest stands of southern finland. Forest Ecology and
Managment, 242 :444–461. 45
Elith, J. and Leathwick, J. (2009). Species distribution models : ecologi-cal explanation and prediction across space and time. Annual Review of
Ecology, Evolution, and Systematics, 40 :677–699. 61
Ellison, A. M. (2004). Bayesian inference in ecology. Ecology Letters, 7 :509– 520. 31
Fan, J. and Jinchi, L. (2010). A selective overview of variable selection in high dimensional feature space. Statistica Sinica, 20 :101–148. 37
FAO (2010). Global forest resources assessment 2010. Forestry Papers. Uni-ted Nations Food and Agriculture Organization, Rome. 20, 21, 26,27 Fayolle, A., Engelbrecht, B., Freycon, V., Mortier, F., Swaine, M., RÃ c
jou-MÃ c chain, M., Doucet, J.-L., Fauvet, N., Cornu, G., and Gourlet-Fleury, S. (2012). Geological substrates shape tree species and trait distributions in African moist forests. Plos One, in press. 34
Flores, O., Rossi, V., and F., M. (2009). Autocorrelation offsets zero-inflation in models of tropical saplings density. Ecological Modeling, 220 :1797–1809. , 32, 34, 39,45
Friedman, J., Hastie, T., and Tibshirani, R. (2010). Regularization paths for generalized linear models via coordinate descent. Journal of Statistical Software, 33 :1–22. 60
Gaetan, C. and Guyon, X. (2008). Modélisation et statistique spatiales. Sprin-ger. 33
Garreta, V., Guiot, J., Mortier, F., Chadoeuf, J., and HÃ c ly, C. (2012). Pollen-based climate reconstruction : Calibration of the vegetation-pollen processes. Ecol. Mod., 235-236 :81–94. 32, 34
Gelfand, A. and Ghosh, S. (1998). Model choice : a minimum posterior predictive loss approach. Biometrika, 85 :1–11. 31
Gelfand, A. E., Banerjee, S., Sirmans, C. F., Tu, Y., and Ong, S. E. (2007). Multilevel modeling using spatial processes : Application to the Singapore housing market. Computational Statistics & Data Analysis, 51 :3567–3579. 40
Gelman, A., Roberts, G., and Gilks, W. (1996). Efficient metropolis jum-ping rules. In Bernardo, J., Berger, J., David, A., and Smith, A., editors,
Bayesian Statistics 5. Oxford University Press. 31
George, E. and McCulloch, R. (1997). Approaches for bayesian variable selection. Statistica Sinica, pages 339–374. 37
Gimenez, O., Buckland, S., Morgan, B., Bez, N., Bertrand, S., Choquet, R., Dray, S., Etienne, M.-P., Fewster, R., Gosselin, F., Mérigot, B., Monestiez, P., Morales, J. M., Mortier, F., Munoz, F., Ovaskainen, O., Pavoine, S., Pradel, R., Schurr, F., Thomas, L., Thuiller, W., Trenkel, V., de Valpine, P., and Rexstad, E. (2014). Statistical ecology comes of age. Biology Letters. 29,31
Golam Kibria, B., Sun, L., Zidek, J. V., and Le, N. D. (2002). Bayesian spatial prediction of random space-time fields with application to mapping PM2.5 exposure. Journal of the American Statistical Association, 97 :112–124. 40 Groll, A. (2015). glmmLasso : Variable Selection for Generalized Linear
Grün, B. and Leisch, F. (2007). Fitting finite mixtures of generalized linear regressions in R. Computational Statistics & Data Analysis, 51 :5247–5252. 36, 60
Grün, B. and Leisch, F. (2008). FlexMix version 2 : Finite mixtures with concomitant variables and varying and constant parameters. Journal of Statistical Software, 28 :1–35. 36,60
Grzebyk, M. and Wackernagel, H. (1994). Multivariate analysis and spa-tial/temporal scales : Real and complex models. In Proceedings of the
XVIIth International Biometric Conference, Hamilton, Ontario. 33
Guillot, G., Estoup, A., Mortier, F., and Cosson, J. (2005a). A spatial sta-tistical model for landscape genetics. Genetics, 170 :1261–1280. 32, 34 Guillot, G., Mortier, F., and Estoup, A. (2005b). Geneland : A program for
landscape genetics. Molecular Ecology Ressources, 5 :712–715. 32,34 Guisan, A. and Zimmermann, N. (2000). Predictive habitat distribution
models in ecology. Ecological Modeling, 135 :147–186. 32
Hoerl, A. and Kennard, R. (1970). Ridge regression : Biased estimation for nonorthogonal problems. Technometrics, 12 :55–67. 37
Hubbell, S. (2001). The Unified Neutral Theory of Biodiversity and Biogeo-graphy. Princeton University Press. 34, 55
Hui, F. C., Warton, D. I., Foster, S. D., and Dunstan, P. K. (2013). To mix or not to mix : comparing the predictive performance of mixture models versus separate species distribution models. Ecology, 94 :1913–1919. 34, 35
Hutchinson, G. (1961). The paradox of the plankton. American Naturalist, 95 :137–147. 34
Joe, H. (1997). Multivariate models and dependence concepts. Monographs on Statistics and Applied Probability. 73. London : Chapman and Hall. xviii, 399 p. . 44
Johnson, S. (2014). The nlopt nonlinear-optimization package. 63
Jones, F. and Muller-Landau, H. (2008). Mesuring long-distance seed dis-persal in complex natural environments : an evaluation and integration of classical and genetic methods. Journal of Ecology, 96 :642–652. 45
Khalili, A. and Chen, J. (2007). Variable selection in finite mixture of regres-sion models. Journal of the American Statistical Association, 102 :1025– 1038. 58, 59
Krige, D. G. (1951). A statistical approach to some basic mine valuation problems on the Witwatersrand. Journal of the Chemical, Metallurgical
and Mining Society of South Africa, 52 :119–139. 32
Kuo, L. and Mallick, B. (1998). Variable selection for regression models. Sankhya : The Indian Journal of Statistics, Series B (1960-2002), 60 :65– 81. 38
Legendre, P. (1993). Spatial autocorrelation : trouble or new paradigm ?
Ecologia, 74 :1659–1673. 28
Leisch, F. (2004). FlexMix : A general framework for finite mixture models and latent class regression in R. Journal of Statistical Software, 11 :1–18. 36, 60
Lexerød, N. L. (2005). Recruitment models for different tree species in Nor-way. Forests Ecology and Management, 206 :91–108. 45
Li, Q. and Lin, N. (2010). The Bayesian Elastic Net. Bayesian Analysis, 5 :151–170. 38
Lourmas, M. (2003). Diversité génétique et aménagement : utilité d’une modélisation intégrée. Bois et Forêts des Tropiques, 276 :85–87. 22 Lunn, D. J., Thomas, A., Best, N., and Spiegelhalter, D. (2000). Winbugs
&ndash ; a bayesian modelling framework : Concepts, structure, and ex-tensibility. Statistics and Computing, 10 :325–337. 31
Lynch, M. and Walsh, B. (1998). Genetics and Analysis of Quantitative
traits. Sinauer Asociates. Sunderland, 980 p. . 27
Marien, J.-N. and Mallet, B. (2004). Nouvelles perspectives pour les planta-tions forestières en afrique centrale. Bois et Forêts des Tropiques, 282 :67– 79. 26
Marin, J.-M. and Robert, C. (2007). Bayesian core : A pratical approach to computational Bayesian statistics. Springer text in statistics. Springer-Verlag, New York, NY. 37,54
Matheron, G. (1963). Traité de géostatistique appliquée. Tome II : le krigeage. Mémoires du BRGM, 24. Éditions Bureau de Recherches Géologiques et Minières, Paris. 32
McBratney, A., Odeh, I., Bishop, T., Dunbar, M., and Shatar, T. (2000). An overview of pedometric techniques for use in soil survey. Geoderma, 97 :293–327. 40
McCullagh, P. and Nelder, J. (1989). Generalized linear models. Monogr. Statist. Appl. Probab. Chapman & Hall/CRC, second edition. 41
McCulloch, C. E., Searle, S. R., and Neuhaus, J. M. (2008). Generalized, Linear, and Mixed Models (Wiley Series in Probability and Statistics). Wiley-Interscience. 33,34
McLachlan, G. and Peel, D. (2004). Finite Mixture Models. Wiley Series in Probability and Statistics. Wiley. 35
McMahon, S. and Diez, J. (2007). Scales of association : hierarchical li-near models and the measurement of ecological systems. Ecology Letters, 10 :437–452. 31
Meuwissen, T., Hayes, B., and M.E., G. (2001). Prediction of total genetic value using genome-wide dense marker maps. Genetics, 157 :1819–1829. 28
Millennium Ecosystem Assessment (2005). Ecosystems and Human Well-being : Biodiversity Synthesis. World Resources Institute, Washington,
DC. 21
Møller, J. and Waagepetersen, R. P. (2004). Statistical inference and simu-lation for spatial point processes. monograph statistics applied probability. Chapman & Hall/CRC, Boca Raton, FL. 43
Mortier, F., Chagneau, P., Etienne, M., Picard, N., Piou, C., and Rossi, V. (2011). Modélisation bayésienne hiérarchique pour l’écologie et la recherche environnementale. 29
Mortier, F., Ouédraogo, D.-Y., Claeys, F., Tadesse, M., Cornu, G., Baya, F., Benedet, F., Freycon, V., Gourlet-Fleury, S., and Picard, N. (2015). Mixture of inhomogeneous matrix models for species-rich ecosystems. En-vironmetrics, 26 :39–51. ,36, 39, 48, 55,66, 68, 69,70
Mortier, F., Rossi, V., Guillot, G., Gourlet-Fleury, S., and Picard, N. (2013). Population dynamics of species-rich ecosystems : the mixture of matrix population models approach. Methods in Ecology and Evolution, 4 :316– 326. , 32, 36, 48,50
Nkoua, M. and Gazull, L. (2013). Les enjeux de la filière “plantations indus-trielles d’eucalyptus” dans la gestion durable du bassin d’approvisionne-ment en bois-énergie de la ville de pointe-noire (république du congo). In Farcy, C., Peyron, J.-L., and Poss, Y., editors, Forêts et foresterie : muta-tions et décloisonnements., pages 175–194, Martinique. Colloque ASRDLF 2011, L’Harmattan. 26
Nobile, A. (2005). Bayesian finite mixtures : a note on prior specification and posterior computation. Technical report, University of Glasgow. 52 Ntzoufras, I., Forster, J., and Dellaportas, P. (2000). Stochastic search
va-riable selection for log-linear models. Journal of Statistical Computation
and Simulation, 68 :23–37. 47
O’Hara, R. and Sillanpää, M. (2009). A review of bayesian variable selection methods : What, how and which. Bayesian Analysis, 4 :85–118. 37 Ouédraogo, D.-Y., Mortier, F., Gourlet-Fleury, S., Freycon, V., and Picard,
N. (2013). Slow-growing species cope best with drought : evidence from long-term measurements in a tropical semi-deciduous moist forest of cen-tral africa. Journal of Ecology, 101 :1459–1470. , 36, 48,55
Parent, E. and Bernier, J. (2007). Le raisonnement bayésien : Modélisation et inférence. Springer. 31
Park, T. and Casella, G. (2008). The Bayesian lasso. Journal of the American Statistical Association, 103 :681–686. 38
Picard, N., Bar-Hen, A., Mortier, F., and Chadoeuf, J. (2008a). Understan-ding the dynamics of an undisturbed tropical rain forest from the spatial pattern of trees. Journal of Ecology, 91 :97–108. 34
Picard, N., Bar-Hen, A., Mortier, F., and Chadœuf, J. (2009). The multi-scale marked area-interaction point processes : a model for the spatial pattern of trees. Scandinavian Journal of Statistics, 36 :23–41. 34
Picard, N., Köhler, P., Mortier, F., and Gourlet-Fleury, S. (2012). A com-parison of five classifications of species into functional groups in tropical forests of French Guiana. Ecological Modeling, 11 :75–83. 55
Picard, N., Mortier, F., and Chagneau, P. (2008b). Influence of estimators of the vital rates in the stock recovery rate when using matrix models for tropical rainforests. Ecological Modelling, 214 :349–360. 57
Plummer, M. (2003). Jags : A program for analysis of bayesian graphical models using gibbs sampling. 31
Raftery, A., Newton, M., Satagopan, J., and Krivitsky, P. (2007). Estimating the integrated likelihood via posterior simulation using the harmonic mean identity (with discussion). In et al., J. B., editor, Bayesian Statistics 8, pages 1–45. Oxford University Press. 31
Richardson, S. and Green, P. J. (1997). On Bayesian analysis of mixtures with an unknown number of components. Journal of the Royal Asiatic Society. Series B, 59 :731–792. 35,52, 53
Roberts, G. and Rosenthal, J. S. (1998). Optimal scaling of discrete approxi-mations to langevin diffusions. Journal of the Royal Asiatic Society. Series
B, 60 :255–268. 43
Roberts, G. O. and Tweedie, R. L. (1996). Exponential convergence of Lange-vin distributions and their discrete approximations. Bernoulli, 2 :341–363. 43
Rogers-Bennett, L. and Rogers, D. (2006). A semi-empirical growth estima-tion method for matrix models of endangered species. Ecological Modelling, 195 :237–246. 57
Rue, H., Martino, S., and Chopin, N. (2009). Approxiamte bayesian inference for latent gaussian models using integrated nested laplace approxiamtions. Journal Of the Royal Statistical Society. Series B, 71 :319–392. 44
Sagnard, F., Pichot, C., Dreyfus, P., Jordano, P., and Fady, B. (2007). Model-ling seed dispersal to predict seedModel-ling recruitment : recolonization dynamics in a plantation forest. Ecological Modeling, 203 :464–474. 45
Schelldorfer, J., Meier, L., Bühlmann, P., Winterthur, A. X. A., and Zürich, E. T. H. (2013). Glmmlasso : An algorithm for high-dimensional generali-zed linear mixed models using l1-penalization. Journal of Computational and Graphical Statistics. 60
Schwarz, G. (1978). Estimating the dimension of a model. Annals of Statis-tics, 6 :461–464. 35
Spiegelhalter, D. J., Best, N. G., Carlin, B. P., and van der Linde, A. (2002). Bayesian measures of model complexity and fit (with discussion). Journal of the Royal Asiatic Society. Series B, 64 :583–639. 31
Städler, N., Bühlmann, P., and Van De Geer, S. (2010). `1-penalization for mixture regression models. Test, 19 :209–256. 58, 59
Steneck, R. and Dethier, M. (1994). A functional group approach to the structure of algal-dominated communities. Oikos, 69 :DOI : 476–498. 34 Swaine, M. and Whitmore, T. (1988). On the definition of ecological species
groups in tropical rain forests. Vegetation, 75 :81–86. 34
Tadesse, M., Sha, N., and Vannucci, M. (2005). Bayesian variable selection in clustering high-dimensional data. Journal of the American Statistical
Association, 100 :602–617. 34
Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Jour-nal of the Royal Statistical Society. Series B, 58 :267–288. 36
Usher, M. (1966). A matrix approach to the management of renewable re-sources, with special reference to selection forests. Journal of Applied Eco-logy, 3 :355–367. 49
Usher, M. (1969). A matrix model for forest management. Journal of Bio-metric Society, 25 :309–315. 49
Vanclay, J. (1992). Modelling regeneration and recruitment in a tropical moist forest. Canadian Journal of Forest Research, 22 :1235–1248. 45 Vanclay, J. (1995). Growth models for tropical forests : A synthesis of models
and methods. Forest Science, 41 :7–42. 48
Varin, C. (2008). On composite marginal likelihoods. Advances in Statistical Analysis, 92 :1–28. 44
Ver Hoef, J. and Barry, R. (1998). Constructing and fitting models for cokri-ging and multivariable spatial prediction. Journal of Statistical Planning and Inference, 69 :275–294. 33, 42
Vigneron, P. (1991). Création et amélioration de variétés hybrides d’euca-lyptus au congo. pages 345–360. 27
Vigneron, P., Bouvet, J.-M., Gouma, R., Saya, A., Gion, J.-M., and Verhae-gen, D. (2000). Eucalypt hybrids breeding in congo. 27
Wackernagel, H. (2003). Multivariate geostatistics. An introduction with ap-plications. . Springer, 3rd completely revised edition. 33
Wikle, C. (2003). Hierarchical Bayesian models for predicting the spread of ecology processes. Ecology, 84 :1382–1394. 30, 31
Wold, H. (1985). Partial least squares. In Kotz, S. Johnson, N. L., editor, Encyclopedia of statistical sciences, pages 581–591. Wiley, New York, 6 edition. 38
Yaglom, A. (1987). Correlation theory of stationary and related random
func-tions. Volume I : Basic results. Springer-Verlag, New York. 42
Zou, H. (2006). The adaptive lasso and its oracle properties. Journal of the American Statistical Association, 101 :1418–1429. 37,58
Zou, H. and Hastie, T. (2005). Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society, Series B, 67 :301–320. 37
Autocorrelation offsets zero-inflation in
models of tropical saplings density
Ecological Modelling 2013ARTICLE IN PRESS
G ModelECOMOD-5376; No. of Pages 13
Ecological Modelling xxx (2009) xxx–xxx
Contents lists available atScienceDirect
Ecological Modelling
j o u r n a l h o m e p a g e :w w w . e l s e v i e r . c o m / l o c a t e / e c o l m o d e l
Autocorrelation offsets zero-inflation in models of tropical saplings density
O. Floresa,∗, V. Rossic, F. Mortierb
aCentre d’Écologie Fonctionnelle et Évolutive, CNRS – UMR 5175, 1919, route de Mende, 34293 Montpellier Cedex 5, France
bCIRAD - UPR Génétique forestière, TA 10/C, Campus international de Baillarguet, 34398 Montpellier Cedex 5, France
cCIRAD - UPR Dynamique des forêts naturelles, TA 10/D, Campus international de Baillarguet, 34398 Montpellier Cedex 5, France
a r t i c l e i n f o
Article history:
Received 10 March 2008
Received in revised form 13 January 2009 Accepted 14 January 2009
Available online xxx
Keywords:
Hierarchical Bayesian Modelling Conditional Auto-Regressive model Variable selection Zero-Inflated Poisson Posterior predictive Paracou French Guiana a b s t r a c t
Modelling the local density of tropical saplings can provide insights into the ecological processes that drive species regeneration and thereby help predict population recovery after disturbance. Yet, few studies have addressed the challenging issues in autocorrelation and zero-inflation of local density. This paper presents Hierarchical Bayesian Modelling (HBM) of sapling density that includes these two features. Special attention is devoted to variable selection, model estimation and comparison.
We developed a Zero-Inflated Poisson (ZIP) model with a latent correlated spatial structure and com-pared it with non-spatial ZIP and Poisson models that were either autocorrelated (Spatial Generalized Linear Mixed, SGLM) or not (generalized linear models, GLM). In our spatial models, local density autocor-relation was modeled by a Conditional Auto-Regressive (CAR) process. 13 explicative variables described ecological conditions with respect to topography, disturbance, stand structure and intraspecific pro-cesses. Models were applied to six tropical tree species with differing biological attributes: Oxandra asbeckii, Eperua falcata, Eperua grandiflora, Dicorynia guianensis, Qualea rosea, and Tachigali melinonii. We built species-specific models using a simple method of variable selection based on a latent binary