Efficient Sampling on the Simplex
Plots and Summaries of RunMh Output
Synthetic Data From a Multinomial Distribution
Logit of a Probability Vector
Finds logit(sp)
Log of the Sum of Probabilities
Computes and
Draw a Proposal on a Simplex
Metropolis Hasting Algorithm Constrained on a Simplex
Efficient Sampling on the Simplex
Plots MCMC Samples on a 3-Simplex
The SALTSampler package facilitates Monte Carlo Markov Chain (MCMC) sampling of random variables on a simplex. A Self-Adjusting Logit Transform (SALT) proposal is used so that sampling is still efficient even in difficult cases, such as those in high dimensions or with parameters that differ by orders of magnitude. Special care is also taken to maintain accuracy even when some coordinates approach 0 or 1 numerically. Diagnostic and graphic functions are included in the package, enabling easy assessment of the convergence and mixing of the chain within the constrained space.