home.md

@@ -27,7 +27,7 @@ Additional models yet to be implemented include:
 
 [MCMCBAYES](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/mcmcBayes.m) numerically performs parameter moment estimation for the variable distributions using statistics from MCMC samples.  An abstract interface to the MCMC sampler is provided through the [MCMCBAYESINTERFACES](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/interfaces/mcmcBayesInterfaces.m) class .  Presently, only the OpenBUGS sampler interface is implemented (see the [MCMCBAYESINTERFACES_OPENBUGS](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/interfaces/mcmcBayesInterfaces_OpenBUGS.m) sub-class).
 
-In addition to easing the burden of implementing multiple models to be compared, [MCMCBAYES](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/mcmcBayes.m) provides automation for the Bayesian analysis.  In particular, one can readily task this class to (1) self-compute analysis results for a dataset using any combination of models listed above, (2) output the MCMC convergence diagnostics for these models, and (3) assess each model's performance against the others using Bayes factors.  To illustrate, the author has provided the [mcmcBayesEvaluateVDMs](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/mcmcBayesEvaluateVDMs.m) class.  [mcmcBayesEvaluateVDMs](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/mcmcBayesEvaluateVDMs.m)provides the capability to automatically task [MCMCBAYES](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/mcmcBayes.m) to simultaneously analyze all eight of the currently implemented models.  As part of the demonstration, over 2000 unique MCMC sampling set requests are setup and performed in OpenBUGS.  MCMC diagnostics and Bayes Factors are additionally generated for the user automatically.  The demonstration sequence is initiated using only a few lines of MATLAB code (see the [gogoBUGS](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/gogoBUGS.m) script).
+In addition to easing the burden of implementing multiple models to be compared, [MCMCBAYES](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/mcmcBayes.m) provides automation for the Bayesian analysis.  In particular, one can readily task this class to (1) self-compute analysis results for a dataset using any combination of models listed above, (2) output the MCMC convergence diagnostics for these models, and (3) assess each model's performance against the others using Bayes factors.  To illustrate, the author has provided the [MCMCBAYESEVALUATEVDMS](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/mcmcBayesEvaluateVDMs.m) class.  [mcmcBayesEvaluateVDMs](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/mcmcBayesEvaluateVDMs.m)provides the capability to automatically task [MCMCBAYES](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/mcmcBayes.m) to simultaneously analyze all eight of the currently implemented models.  As part of the demonstration, over 2000 unique MCMC sampling set requests are setup and performed in OpenBUGS.  MCMC diagnostics and Bayes Factors are additionally generated for the user automatically.  The demonstration sequence is initiated using only a few lines of MATLAB code (see the [GOGOBUGS](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/gogoBUGS.m) script).
 
 [MCMCBAYES](https://gitlab.com/reubenajohnston/mcmcBayes/blob/master/matlab/mcmcBayes.m) provides the following statistical diagnostics for MCMC sampling of model variable distribution: mean, standard deviation, highest posterior density (Chen, Shao 1999), and Monte-Carlo error (using batch mean estimation method, see Hastings 1970).  Additionally, it provides graphical diagnostics in the form of density plots, trace (i.e., raw sample) plots, ergodic mean plots, and autocorrelation function plots.