[Depmix-commits] r556 - in pkg/depmixS4: . inst/doc man

[noreply at r-forge.r-project.org]

Author: ingmarvisser
Date: 2012-07-31 18:19:28 +0200 (Tue, 31 Jul 2012)
New Revision: 556

Modified:
   pkg/depmixS4/NEWS
   pkg/depmixS4/README
   pkg/depmixS4/inst/doc/depmixS4.Rnw
   pkg/depmixS4/man/depmixS4-package.Rd
Log:
Minor changes related to classification likelihood and show/summary

Modified: pkg/depmixS4/NEWS
===================================================================
--- pkg/depmixS4/NEWS	2012-07-31 14:23:14 UTC (rev 555)
+++ pkg/depmixS4/NEWS	2012-07-31 16:19:28 UTC (rev 556)
@@ -2,16 +2,19 @@
 
 Major changes
 
-  o Fit will now allow a choice between maximising the regular or 
-    classification likelihood.
+	o The EM algorithm has gained an extra argument 'classification',
+		passed from the 'fit' function using argument 'emcontrol', to allow a
+		choice between maximising the regular (classification="soft", the
+		default) or classification (classification="hard") likelihood.
 
-  o Parameters are now given proper names, following the glm() scheme 
-	  (e.g. '(Intercept)', 'x' et cetera); with this, the show and summary 
-		methods have changed considerably and now produce more compact and 
-		more readable output. The summary method (for both fitted and unfitted 
-    models) now has an argument 'compact' that controls the presentation of 
-    the repsonse model parameters. The prior and transition models are now
-    presented more compactly when there are no covariates. 
+	o Parameters are now given proper names, following the glm() scheme
+		(e.g. '(Intercept)', 'x1', et cetera); with this, the show and summary
+		methods have changed considerably and now produce more compact and more
+		readable output.  The summary method (for both fitted and unfitted
+		models) now has an argument 'compact' (TRUE by default) that controls
+		the presentation of the repsonse model parameters.  The prior and
+		transition models are now presented more compactly when there are no
+		covariates.
 
 Minor changes
 

Modified: pkg/depmixS4/README
===================================================================
--- pkg/depmixS4/README	2012-07-31 14:23:14 UTC (rev 555)
+++ pkg/depmixS4/README	2012-07-31 16:19:28 UTC (rev 556)
@@ -13,7 +13,7 @@
 default when no covariates are present) with the possibility of including
 covariates.
 
-Optimization is by default done using the EM algorithm.  When linear
+Optimization is by default done using the EM algorithm.  When (linear)
 constraints are included, package Rsolnp is used for optimization (there is
 also support for using Rdonlp2 as optimizer, see USING RDONLP2 below).  New
 response distributions can be added by extending the response-class and

Modified: pkg/depmixS4/inst/doc/depmixS4.Rnw
===================================================================
--- pkg/depmixS4/inst/doc/depmixS4.Rnw	2012-07-31 14:23:14 UTC (rev 555)
+++ pkg/depmixS4/inst/doc/depmixS4.Rnw	2012-07-31 16:19:28 UTC (rev 556)
@@ -28,7 +28,7 @@
 	(slightly) modified version of \cite{Visser+Speekenbrink:2010},
 	published in the \emph{Journal of Statistical Software}.  Please
 	refer to that article when using \pkg{depmixS4}.  The current
-	version is 1.2-0; the version history and changes can be found in
+	version is 1.3-0; the version history and changes can be found in
 	the NEWS file of the package. Below, the major versions are listed 
 	along with the most noteworthy changes. 
 
@@ -76,11 +76,31 @@
 \section*{Version history}
 
 \begin{description}
+		\item[1.3-0] The EM algorithm has gained an extra argument
+		\code{classification}, passed from the \code{fit} function using
+		argument \code{emcontrol}, to allow a choice between maximising
+		the regular (\code{classification="soft"}, the default) or
+		classification (\code{classification="hard"}) likelihood.  See
+		section~???  for details.
+		
+		Parameters are now given proper names, following the \code{glm()}
+		scheme (e.g. \code{(Intercept)}, \code{x1}, et cetera); with this,
+		the \code{show} and \code{summary} methods have changed
+		considerably and now produce more compact and more readable
+		output.  The \code{summary} method (for both fitted and unfitted
+		models) now has an argument \code{compact} (\code{TRUE}
+		by default) that controls the presentation of the repsonse model
+		parameters.  The prior and transition models are now presented
+		more compactly when there are no covariates.
+		
 		\item[1.2-0] Added support for missing data, see 
 		section~\ref{sec:missingdata}.
+		
 		\item[1.1-0] Speed improvements due to writing the main loop in C code.
+		
 		\item[1.0-0] First release with this vignette, a modified version 
 		of the paper in the Journal of Statistical Software. 
+		
 		\item[0.1-0] First version on CRAN. 
 \end{description}
 

Modified: pkg/depmixS4/man/depmixS4-package.Rd
===================================================================
--- pkg/depmixS4/man/depmixS4-package.Rd	2012-07-31 14:23:14 UTC (rev 555)
+++ pkg/depmixS4/man/depmixS4-package.Rd	2012-07-31 16:19:28 UTC (rev 556)
@@ -34,8 +34,8 @@
 	\tabular{ll}{
 		Package: \tab depmixS4\cr
 		Type: \tab Package\cr
-		Version: \tab 1.2-0\cr
-		Date: \tab 2012-06-15\cr
+		Version: \tab 1.3-0\cr
+		Date: \tab 2012-07-31\cr
 		License: \tab GPL\cr
 	}