Learn R Programming

ggmcmc

ggmcmc is a tool for assessing and diagnosing convergence of Markov Chain Monte Carlo simulations, as well as for graphically display results from full MCMC analysis. The package also facilitates the graphical interpretation of models by providing flexible functions to plot the results against observed variables.

To install or update, run:

install.packages("ggmcmc", dependencies=TRUE)

Check the main page with resources for ggmcmc.

Report bugs, request improvements, ask questions or provide ideas at the issues page.

Copy Link

Version

Install

install.packages('ggmcmc')

Monthly Downloads

2,525

Version

1.5.1.1

License

GPL-2

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/xfim/ggmcmc/

Homepage

http://xavier-fim.net/packages/ggmcmc/

Maintainer

Xavier i Marín

Last Published

February 10th, 2021

Functions in ggmcmc (1.5.1.1)

Calculate the autocorrelation of a single chain, for a specified amount of lags

Dotplot of Potential Scale Reduction Factor (Rhat)

Calculate binwidths by parameter, based on the total number of bins.

Calculate Credible Intervals (wide and narrow).

Auxiliary function that sorts Parameter names taking into account numeric values

Dotplot of the effective number of independent draws

Dotplot of the Geweke diagnostic, the standard Z-score

ggs_diagnostics

Formal diagnostics of convergence and sampling quality

Density plots of the chains

Simulated data for a binary logistic regression and its MCMC samples

ggs_autocorrelation

Plot an autocorrelation matrix

Subset a ggs object to get only the parameters with a given regular expression.

Spectral Density Estimate at Zero Frequency.

ggs_compare_partial

Density plots comparing the distribution of the whole chain with only its last part.

Wrapper function that creates a single pdf file with all plots that ggmcmc can produce.

ggs_caterpillar

Caterpillar plot with thick and thin CI

Auxiliary function that extracts information from a single chain.

Separation plot for models with binary response variables

Import MCMC samples into a ggs object than can be used by all ggs_* graphical functions.

Values for the observed outcome of a simple linear regression with fake data.

Generate a factor with unequal number of repetitions.

ggs_crosscorrelation

Plot the Cross-correlation between-chains

Create a plot matrix of posterior simulations

Simulated data for a continuous linear regression and its MCMC samples

Simulations of the parameters of a simple linear regression with fake data.

Simulations of the posterior predictive distribution of a simple linear regression with fake data.

Posterior predictive plot comparing the outcome standard deviation vs the distribution of the predicted posterior standard deviations.

Posterior predictive plot comparing the outcome mean vs the distribution of the predicted posterior means.

Traceplot of the chains

Values for the observed outcome of a binary logistic regression with fake data.

Plot for model fit of binary response variables: percent correctly predicted

Simulations of the parameters of a simple linear regression with fake data.

Calculate the ROC curve for a set of observed outcomes and predicted probabilities

Histograms of the paramters.

Receiver-Operator Characteristic (ROC) plot for models with binary outcomes

Gelman-Rubin-Brooks plot (Rhat shrinkage)

Running means of the chains

Simulations of the parameters of a hierarchical model

Generate a data frame suitable for matching parameter names with their labels