clinDR: mcmc.control – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

mcmc.control

Settings for restan execution in function fitEmaxB

Set MCMC controls. Also control spread of initial parameter values.

mcmc.control(chains = 1, thin = 1, 
	warmup = 1000, iter = 3333* thin+warmup, 
	propInit = 0.25, seed = 12357, adapt_delta = 0.95)

`chains`	Number of chains
`thin`	Number of discarded sampled parameter values. `warmup` and `iter` include `thin`, so for example, to output `1000` samples, `iter` must be `1000` times `thin`.
`warmup`	See `rstan` documentation for function `sampling`.
`iter`	See `rstan` documentation for function `sampling`.
`propInit`	Initial values for `E0` and `Emax` are derived from the prior mean plus/minus `propInit` times the prior SD. `propInit` can be set to a small proportion if very diffuse prior distributions are specified.
`seed`	Seed passed to `rstan`.
`adapt_delta`	See `rstan` documentation for function `sampling`.

Some defaults were changed with version>=2.0. For earlier versions, warmup = 500, iter = 5000* thin, and adapt_delta=0.8

Simulation and Analysis Tools for Clinical Dose Response Modeling

v2.3.5

GPL (>= 2)

Authors

Neal Thomas [aut, cre] (<https://orcid.org/0000-0002-1915-8487>), Jing Wu [aut], Mike K. Smith [aut]

Initial release

2021-04-11