Calculates the Gelman-Rubin criterion for convergence (uses gelman.diag from package coda).

GR_crit(object, confidence = 0.95, transform = FALSE, autoburnin = TRUE,
multivariate = TRUE, subset = NULL, exclude_chains = NULL,
start = NULL, end = NULL, thin = NULL, warn = TRUE, mess = TRUE,
...)

Arguments

object object inheriting from class 'JointAI' the coverage probability of the confidence interval for the potential scale reduction factor a logical flag indicating whether variables in x should be transformed to improve the normality of the distribution. If set to TRUE, a log transform or logit transform, as appropriate, will be applied. a logical flag indicating whether only the second half of the series should be used in the computation. If set to TRUE (default) and start(x) is less than end(x)/2 then start of series will be adjusted so that only second half of series is used. a logical flag indicating whether the multivariate potential scale reduction factor should be calculated for multivariate chains subset of parameters/variables/nodes (columns in the MCMC sample). Follows the same principle as the argument monitor_params in *_imp. optional vector of the index numbers of chains that should be excluded the first iteration of interest (see window.mcmc) the last iteration of interest (see window.mcmc) thinning interval (integer; see window.mcmc). For example, thin = 1 (default) will keep the MCMC samples from all iterations; thin = 5 would only keep every 5th iteration. logical; should warnings be given? Default is TRUE. logical; should messages be given? Default is TRUE. currently not used

References

Gelman, A and Rubin, DB (1992) Inference from iterative simulation using multiple sequences, Statistical Science, 7, 457-511.

Brooks, SP. and Gelman, A. (1998) General methods for monitoring convergence of iterative simulations. Journal of Computational and Graphical Statistics, 7, 434-455.

The vignette Parameter Selection contains some examples how to specify the argument subset.

Examples

mod1 <- lm_imp(y ~ C1 + C2 + M2, data = wideDF, n.iter = 100)
GR_crit(mod1)
#> Potential scale reduction factors:
#>
#>             Point est. Upper C.I.
#> (Intercept)      1.004       1.02
#> C1               1.003       1.02
#> C2               0.999       1.00
#> M22              1.005       1.01
#> M23              1.004       1.03
#> M24              1.003       1.02
#> sigma_y          1.001       1.00
#>
#> Multivariate psrf
#>
#> 1.01