Nathalie Peyrard is a Senior Scientist at INRAE. Most of her current research focuses on computational statistics, with applications in ecology.Olivier Gimenez is a Senior Scientist at CNRS. His research focuses on animal ecology, statistical modeling and social sciences.

• Introduction xiNathalie PEYRARD, Stéphane ROBIN and Olivier GIMENEZChapter 1. Trajectory Reconstruction and Behavior Identification Using Geolocation Data 1Marie-Pierre ETIENNE and Pierre GLOAGUEN1.1. Introduction 11.1.1. Reconstructing a real trajectory from imperfect observations 11.1.2. Identifying different behaviors in movement 31.2. Hierarchical models of movement 31.2.1. Trajectory reconstruction model 31.2.2. Activity reconstruction model 61.3. Case study: masked booby, Sula dactylatra (originals) 141.3.1. Data 141.3.2. Projection 151.3.3. Data smoothing 151.3.4. Identification of different activities through movement 161.3.5. Results 171.4. References 23Chapter 2. Detection of Eco-Evolutionary Processes in the Wild: Evolutionary Trade-Offs Between Life History Traits 27Valentin JOURNÉ, Sarah CUBAYNES, Julien PAPAÏX and Mathieu BUORO2.1. Context 272.2. The correlative approach to detecting evolutionary trade-offs in natural settings: problems 282.2.1. Mechanistic and statistical modeling as a means of accessing hidden variables 292.3. Case study 312.3.1. Costs of maturing and migration for survival: a theoretical approach 312.3.2. Growth/reproduction trade-off in trees 372.4. References 44Chapter 3. Studying Species Demography and Distribution in Natural Conditions: Hidden Markov Models 47Olivier GIMENEZ, Julie LOUVRIER, Valentin LAURET and Nina SANTOSTASI3.1. Introduction 473.2. Overview of HMMs 483.3. HMM and demography 503.3.1. General overview 503.3.2. Case study: estimating the prevalence of dog–wolf hybrids with uncertain individual identification 543.4. HMM and species distribution 553.4.1. General case 553.4.2. Case study: estimating the distribution of a wolf population with species identification errors and heterogeneous detection 573.5. Discussion 603.6. Acknowledgments 623.7. References 62Chapter 4. Inferring Mechanistic Models in Spatial Ecology Using a Mechanistic-Statistical Approach 69Julien PAPAÏX, Samuel SOUBEYRAND, Olivier BONNEFON, Emily WALKER, Julie LOUVRIER, Etienne KLEIN and Lionel ROQUES4.1. Introduction 694.2. Dynamic systems in ecology 704.2.1. Temporal models 704.2.2. Spatio-temporal models without reproduction 744.2.3. Spatio-temporal models with reproduction 764.2.4. Numerical solution 774.3. Estimation 774.3.1. Estimation principle 774.3.2. Parameter estimation 784.3.3. Estimation of latent processes 804.3.4. Mechanistic-statistical models 824.4. Examples 834.4.1. The COVID-19 epidemic in France 834.4.2. Wolf (Canis lupus) colonization in southeastern France 864.4.3. Estimating dates and locations of the introduction of invasive strains of watermelon mosaic virus 904.5. References 94Chapter 5. Using Coupled Hidden Markov Chains to Estimate Colonization and Seed Bank Survival in a Metapopulation of Annual Plants 97Pierre-Olivier CHEPTOU, Stéphane CORDEAU, Sebastian LE COZ and Nathalie PEYRARD5.1. Introduction 975.2. Metapopulation model for plants: introduction of a dormant state 995.2.1. Dependency structure in the model 995.2.2. Distributions defining the model 1005.2.3. Parameterizing the model 1015.2.4. Linking the parameters of the model with the ecological parameters of the dynamics of an annual plant 1035.2.5. Estimation 1045.2.6. Model selection 1055.3. Dynamics of weed species in cultivated parcels 1055.3.1. Dormancy and weed management in agroecosystems 1055.3.2. Description of the data set 1065.3.3. Comparison with an HMM with independent patches 1085.3.4. Influence of crops on weed dynamics 1095.4. Discussion and conclusion 1105.5. Acknowledgments 1135.6. References 113Chapter 6. Using Latent Block Models to Detect Structure in Ecological Networks 117Julie AUBERT, Pierre BARBILLON, Sophie DONNET and Vincent MIELE6.1. Introduction 1176.2. Formalism 1196.3. Probabilistic mixture models for networks 1206.3.1. SBMs for unipartite networks 1216.3.2. Stochastic block model for bipartite networks 1226.4. Statistical inference 1246.4.1. Estimation of parameters and clustering 1256.4.2. Model selection 1266.5. Application 1276.5.1. Food web 1276.5.2. A bipartite plant–pollinator network 1296.6. Conclusion 1306.7. References 132Chapter 7. Latent Factor Models: A Tool for Dimension Reduction in Joint Species Distribution Models 135Daria BYSTROVA, Giovanni POGGIATO, Julyan ARBEL and Wilfried THUILLER7.1. Introduction 1357.2. Joint species distribution models 1387.3. Dimension reduction with latent factors 1397.4. Inference 1407.5. Ecological interpretation of latent factors 1417.6. On the interpretation of JSDMs 1427.7. Case study 1427.7.1. Introduction of the dataset 1427.7.2. R package used 1447.7.3. Implementation and convergence diagnosis 1447.7.4. Results and discussion 1447.8. Conclusion 1527.9. References 153Chapter 8. The Poisson Log-Normal Model: A Generic Framework for Analyzing Joint Abundance Distributions 157Julien CHIQUET, Marie-Josée CROS, Mahendra MARIADASSOU, Nathalie PEYRARD and Stéphane ROBIN8.1. Introduction 1578.2. The Poisson log-normal model 1598.2.1. The model 1598.2.2. Inference method 1628.2.3. Dimension reduction 1648.2.4. Inferring networks of interaction 1658.3. Data analysis: marine species 1678.3.1. Description of the data 1678.3.2. Effects due to site and date 1688.3.3. Dimension reduction 1708.3.4. Inferring ecological interactions 1718.4. Discussion 1768.5. Acknowledgments 1778.6. References 177Chapter 9. Supervised Component-Based Generalized Linear Regression: Method and Extensions 181Frédéric MORTIER, Jocelyn CHAUVET, Catherine TROTTIER, Guillaume CORNU and Xavier BRY9.1. Introduction 1819.2. Models and methods 1849.2.1. Supervised component-based generalized linear regression 1849.2.2. Thematic supervised component-based generalized linear regression (THEME-SCGLR) 1879.2.3. Mixed SCGLR 1899.3. Case study: predicting the abundance of 15 common tree species in the forests of Central Africa 1919.3.1. The SCGLR method: a direct approach 1919.3.2. THEME-SCGLR: improved characterization of predictive components 1949.3.3. Mixed-SCGLR: taking account of the concession effect 1969.4. Discussion 2009.5. References 201Chapter 10. Structural Equation Models for the Study of Ecosystems and Socio-Ecosystems 203Fabien LAROCHE, Jérémy FROIDEVAUX, Laurent LARRIEU and Michel GOULARD10.1. Introduction 20310.1.1. Ecological background 20310.1.2. Methodological problem 20410.1.3. Case study: biodiversity in a managed forest 20510.2. Structural equation model 20610.2.1. Hypotheses and general structure of an SEM 20610.2.2. Likelihood and estimation in an SEM 20910.2.3. Fit quality and nested SEM tests 21110.3. Case study: biodiversity in managed forests 21310.3.1. Preliminary steps 21310.3.2. Evaluating the measurement model alone 21310.3.3. Evaluating the relational model 21410.3.4. Significance of parameters in the relational model 21910.3.5. Findings 22110.4. Discussion 22310.4.1. A confirmatory approach 22310.4.2. Gaussian framework 22410.4.3. Centered-reduced observed variables 22410.4.4. Structural constraints 22410.4.5. Use of resampling 22510.5. Acknowledgments 22510.6. References 226List of Authors 229Index 233