get_model: Generate model code for passage to stan
In faulknerjam/bnps: Shrinkage-Prior Markov Random Field Smoothing

Description Usage Arguments Details Value See Also

Generates a text string of code describing the model of interest for passage to the stan function in the rstan package. This function is called internally in the spmrf function.

1 2	get_model(prior = "horseshoe", likelihood = "normal", order = 1, zeta = 0.01, save.loglik = FALSE)

`prior`	A character string specifying which prior to use on order-k differences. Choices are "horseshoe", "laplace", and "normal". Note that "laplace" priors are currently not available for coalescent likelihoods.
`likelihood`	A character string specifying the probability distribution of the observation variable. Current choices are "normal", "poisson", "binomial", and "coalescent".
`order`	Numeric value specifying order of differencing (1, 2, or 3). Note that order 3 is currently not available for coalescent likelihoods.
`zeta`	The hyperparameter for the global smoothing parameter gamma. This is the scale parameter of a half-Cauchy distribution. Smaller values will result in more smoothing depending on the prior specification and the strength of the data. Values must be > 0.
`save.loglik`	Logical flag for whether to calculate the individual components of the log-likelihood for use in calculating WAIC or LOOIC with the `loo` package. Default is FALSE.

This function can be used to generate a text string containing code in the stan model syntax. This function is called by the spmrf function internally, so it is not necessary to use get_model external to spmrf.

A character string of code describing the model of interest for passage to the function stan in the rstan package.

spmrf, stan, get_init

faulknerjam/bnps documentation built on Sept. 26, 2020, 8:07 p.m.