Quick commands from R
Run these helpers inside R to list every model family, prior, or likelihood that ships with INLA.
# Discover the available sections (latent, likelihood, prior, ...)
inla.list.models()
# Focus on a specific family
inla.list.models("prior")
# Read the inline documentation for a component
inla.doc("loggamma")
Try swapping "prior" for "group", "hazard", "latent", "likelihood", "link", or "mix" to zoom in on that category.
Selected latent models
Popular latent specifications with working examples. Browse the full library at inla.r-inla-download.org/r-inla.org/doc/latent/.
- Autoregressive model of order 1
- Autoregressive model of order p
- Besag model for spatial effects
- dMatern latent model
- Generic0 model
- Correlated random effects (iid)
- Random walk model of order 1
- Random walk model of order 2
- Seasonal variation model
- Lognormal latent model
Each model entry includes hyperparameter defaults, constraints, and the matching inla.doc() key.
Selected priors
Frequently used priors and their parameterisations. Explore every prior PDF at inla.r-inla-download.org/r-inla.org/doc/prior/.
- Beta prior for correlation parameters
- Dirichlet prior
- Expression (custom) prior
- Gaussian prior
- Logit-Beta prior
- PC prior for correlation ρ (base model ρ = 0)
- PC prior for correlation ρ (base model ρ = 1)
- PC prior for degrees of freedom
- PC prior for Gamma shape
- PC prior for precision
Use inla.prior.control() to apply these priors directly inside your model definitions.
Selected likelihoods
Likelihood families with simulated examples and parameter details. Browse the full catalogue at inla.r-inla-download.org/r-inla.org/doc/likelihood/.
- Beta distribution
- Beta-Binomial distribution
- Binomial distribution
- Censored Poisson distribution
- Exponential distribution
- Gamma distribution
- Gaussian distribution
- Logistic distribution
- Lognormal distribution
- Poisson distribution
Combine likelihood entries with the latent model listings above to assemble complete joint models.
Key vignettes & tutorials
- SPDE one-dimensional example
- Introduction to fitting SPDE models
- Blended GEV tutorial
- Conditional sampling from a fitted model
- Conditional logistic regression
- User-defined integration points
- Defining latent models via
rgeneric - Multinomial logit models
- Approximating joint marginals
- Scaling IGMRF models
Need the raw data or code?
The function reference includes reproducible examples plus datasets such as Scotland, Seeds, and Munich. You can load them directly in R after attaching the INLA package:
library(INLA)
data("Scotland")
str(Scotland)
Looking for something specific? Use the search box on the function reference page, or run inla.doc("<keyword>") in R.