gamBayes: Bayesian GAMs

In abnormally-distributed/Bayezilla: Bayesian Models With JAGS and Several Utilities for Data Exploration and Model Evaluation.

Description

This implements generalized additive models (GAMs) via the basis functions available in the splines and splines2 packages. For example, you can use bs(), ns(), cSpline(), iSpline(), mSpline(), or the base R function poly() to generate basis functions for the variables intended for non-linear modeling. The basis functions are regularized using a hierarchical prior where the shrinkage parameter for each predictor is given a DuMouchel's prior. Note that predictor specific means for each variable represented by a basis function of n terms, all n terms share a shrinkage parameter. This is standard procedure for GAMs.

Usage

gamBayes(formula, data, family = "gaussian", log_lik = FALSE,
  iter = 4000, warmup = 1000, adapt = 1000, chains = 4, thin = 1,
  method = "rjparallel", cl = makeCluster(2), ...)

Arguments

formula	the model formula
data	a data frame
family	one of "gaussian", "st" (Student-t with nu=3), "binomial", or "poisson".
log_lik	Should the log likelihood be monitored? The default is FALSE.
iter	How many post-warmup samples? Defaults to 4000.
warmup	How many warmup samples? Defaults to 1000.
adapt	How many adaptation steps? Defaults to 1000.
chains	How many chains? Defaults to 4.
thin	Thinning interval. Defaults to 1.
method	Defaults to "rjparallel". Otherwise, "rjags" (single core run).
cl	Use parallel::makeCluster(# clusters) to specify clusters for the parallel methods. Defaults to two cores.
...	Other arguments to run.jags.
df	degrees of freedom for prior.
s	The desired prior scale. Defaults to 1. Is automatically squared within the model so select a number here on the standard deviation scale.

Value

A run.jags object

Examples

gamBayes()

abnormally-distributed/Bayezilla documentation built on Oct. 31, 2019, 1:57 a.m.