What good fortune that I looked up advances in Bayesian methods the day a new task view was published! If you’re just starting with Bayes, they even have packages listed here designed to help you learn. I’ve been using R-INLA and for a few reasons I became curious what else was out there. I’m still assuming Laplace estimations are faster than Markov chain Monte Carlo, so there are more on the list that might be good to check out if I abandon that method altogether.
- LaPlace’s Demon, iter-lap: This one appealed to me as an alternative to R-INLA
- arm, RSGHB: might be worth checking out for hierarchical models
- Bayes images: image analysis
- Bayes meta, bspmma: meta-analysis
- Bayes tree,tgp: Bayesian additive regression trees (BART)
- Bayes QR: quantile regression
- Bayes var-sel: variable selection
- deal, ebdb Net, grain, network change (etc. see this link): network analysis
- FME: an alternative to deSolve
- hbsae: small area estimates
- spBayes: spatial
- spikeSlabGAM: geo-additive
- spTimer: space-time
- ramps: geo-statistical
There are also interesting choices for model averaging (and ensembles), time series, extreme value, clustering, threshold, change point and auto-regressive models.