Run the Monte Carlo study by KLTG (2016), or a smaller version thereof
run_mcstudy(s = 2, a = 0.5, n = 12, nr_iterations = 50, zoom = FALSE,
random_seed = 816)Parameters characterizing the process from which data are simulated (see Section 4 and Table 4 of KLTG, 2016). Defaults to the values reported in the main text of the paper.
Number of Monte Carlo iterations (defaults to 50).
Set to TRUE to produce results for a fine grid of small (MCMC) sample sizes, as in Figure 2 of KLTG (2016).
Seed used for running the simulation experiment. Defaults to 816.
Object of class "mcstudy", containing the results of the analysis. This object can be passed to plot for plotting, see the documentation for plot.mcstudy.
The full results in Section 4 of KLTG (2016) are based on s = 2, a = 0.5,
n = 12 and nr_iterations = 1000. Producing these results takes about 140 minutes on an
Intel i7 processor.
Krueger, F., S. Lerch, T.L. Thorarinsdottir and T. Gneiting (2016), `Probabilistic forecasting and comparative model assessment based on Markov Chain Monte Carlo output', working paper, Heidelberg Institute for Theoretical Studies, available at http://arxiv.org/abs/1608.06802.
plot.mcstudy produces a summary plot of the results generated by run_mcstudy