Package: INLA 26.09.17

Introduction | Model | Environment | Import data | Make spatial data | SPDE components | Modeling mesh | SPDE model object | Index sets | Projector matrices | Data stack for model fitting | Model formula | Run model | Model summaries | SVC maps | More information | Citations

Introduction | First example | Example with replicate/group | The z model | Using replicate, again | Using 'Alocal' in copy

Introduction | An example | Another example

Introduction

References

Contents | Introduction | User-defined priors for the hyperparameters | Does INLA support the use of different link-functions? | How can I do predictions using INLA? | Some of the models needs a graph, how do I specify it? | How \texttt | Can INLA deal with missing covariates? | Compute cross-validation or predictive measures of fit | I have access to a remote Linux/MacOS server, is it possible to run the computations remotely and running R locally? | Posteriors for linear combinations | INLA seems to work great for near all cases, but are there cases where INLA is known to have problems? | Can I have the linear predictor from one model as a covariate in a different model? | Latent models, likelihoods and priors. | Copying a model | Replicate a model | Models with more than one type of likelihood | Models where the response/data depends on linear combinations of the "linear predictor" (or the sum of "fixed" and "random" effects)

Abstract | Introduction | The spatial domain | A spatial field | Spatial sub-domains | Covariates | Outcomes | First outcome: aggregated Gaussian | Second outcome: Survival | Third outcome: Count under exposure | Data model setup | SPDE model setup | Linear predictor components | Building data stacks | Fitting the model and some results | Model fitting | Summaries | Results considering each outcome | References

Abstract | Theoretical part | On the Multinomial logit model | On the Poisson Trick | Practical Part | On the Multinomial Data and Model Parameters | Data structure | A Simple Model | Changing the size | A First Random Effect | Time Random Effects | Discrete Spatial Random effect | Continuos spatial random effect | Yogurt Data | Model | Conclusion | References

An introduction to the Logistic Normal Dirichlet Regression | Simulated example I (Type II) | Data simulation | Defining hyperparameters and dimensionality of the response | Simulating a covariate | alr-coordinates | Data in the simplex | Plotting the simulated data | Data preparation for fitting | Index for individual | Extending the dataset | Response in R-INLA | Covariates in R-INLA | inla.stack | Fitting the model | Fit in R-INLA | Marginal posterior distribution of the fixed effects | Marginal Posterior distribution of the hyperparameters | Predicting for a new observation | Preparing dataset for predictions | Preparing inla.stack for predictions | Prediction | Extracting predictions using inla.posterior.sample | Predictions in the simplex | References

A reparametrisation of the GEV | The blended GEV model | Simulated example 1 | Data simulation | Prior specification | Control variables | INLA fit | Simulated example 2 | Data simulation | Prior specification | INLA fit | Simulated example 3 | Data simulation | INLA fit | Notes | Linear predictor for the bGEV model | PC prior for the tail parameter | About $\texttt | Tools

Introduction | Theory reference | First example | Deterministic Joint approximation | References

Introduction | First example | Second example

Introduction | Working with factors in R | Dealing with factors in inla.stack() | When there is a prediction scenario | References

Installation Procedures

Introduction | Simple example | Samples of hyper-parameters | Example: Predictor with and without random effects | Predictor $A$-matrix (experimental-mode only)

Parametrization | Hyperparameters | Specification | Example | References