florianhartig / BayesianTools

General-Purpose MCMC and SMC Samplers and Tools for Bayesian Statistics
https://cran.r-project.org/web/packages/BayesianTools/index.html
117 stars 29 forks source link

Consider burnin in chain iterations #194

Open florianhartig opened 4 years ago

florianhartig commented 4 years ago

Looking at https://github.com/florianhartig/BayesianTools/issues/193, I noted that burnin is not considered when labeling the iterations of the chain, for example

set.seed(1234)
settings = list(iterations = 300, burnin=100)
out <- runMCMC(bayesianSetup = bayesianSetup, sampler = "Metropolis", settings = settings)
plot(out)

goes from 0 to 200. I'm not sure if that was on purpose at some point, but it's different to how Jags behaves, for example. Change?