[Vegan-commits] r1955 - pkg/vegan/inst

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

Author: jarioksa
Date: 2011-10-19 21:05:11 +0200 (Wed, 19 Oct 2011)
New Revision: 1955

Modified:
   pkg/vegan/inst/NEWS.Rd
Log:
merge NEWS from branches/2.0

Modified: pkg/vegan/inst/NEWS.Rd
===================================================================
--- pkg/vegan/inst/NEWS.Rd	2011-10-18 17:52:32 UTC (rev 1954)
+++ pkg/vegan/inst/NEWS.Rd	2011-10-19 19:05:11 UTC (rev 1955)
@@ -13,11 +13,17 @@
       habitat types or sampling units, and is applicable only to count
       data with no over-dispersion.
 
+      \item \code{as.preston} gained \code{plot} and \code{lines}, and
+      \code{as.fisher} gained \code{plot} method (which also can add
+      items to existing plots). These are similar as \code{plot} and
+      \code{lines} for \code{prestonfit} and \code{fisherfit}, but
+      display only data without the fitted model.
+
       \item \code{raupcrick}: new function to implement Raup-Crick
       dissimilarity as a probability of number of co-occurring species
       with occurrence probabilities proportional to species
       frequencies.  \pkg{Vegan} has Raup-Crick index as a choice in
-      \code{vegdist}, but it uses equal sampling probabilities for
+      \code{vegdist}, but that uses equal sampling probabilities for
       species and analytic equations. The new \code{raupcrick}
       function uses simulation with \code{oecosimu}. The function
       follows Chase et al. (2011) \emph{Ecosphere} 2:art24
@@ -30,16 +36,44 @@
   \subsection{BUG FIXES}{
     \itemize{
 
-      \item Function \code{meandist} could randomly permute items,
-      especially when the \code{grouping} was numerical. The problem
-      was reported by Dr Miguel Alvarez (Univ. Bonn).
+      \item Function \code{meandist} can scramble items and confusing
+      results, especially when the \code{grouping} was numerical. The
+      problem was reported by Dr Miguel Alvarez (Univ. Bonn).
 
+      \item \code{metaMDS} did not reset \code{tries} when a new model
+      was started with a \code{previous.best} solution from a different
+      model. 
+
       \item Function \code{permatswap} for community null models using
       quantitative swap never swapped items in a \eqn{2 \times 2}{2 by 2}
       submatrix if all cells were filled.
 
+      \item The result from \code{permutest.cca} could not be
+      \code{update}d because of a \file{NAMESPACE} issue.
+
+      \item \R 2.14.0 changed so that it does not accept using
+      \code{sd()} function for matrices, and several \pkg{vegan}
+      functions were changed to adapt to these changes (\code{rda},
+      \code{capscale}, \code{simulate} methods for \code{rda},
+      \code{cca} and \code{capscale}). The change in \R 2.14.0 does
+      not change the results but causes a lot of annoying warnings in
+      \code{rda} and related functions, and you probably wish to
+      upgrade \pkg{vegan}.
+
     }	
   } % end BUG FIXES
+
+  \subsection{ANALYSES}{
+    \itemize{
+
+      \item \code{nesteddisc} is slacker and hence faster when trying
+      to optimize the statistic for tied column frequencies. Tracing
+      showed that in most cases an improved ordering was found rather
+      early in tries, and the results are equally good in most cases.
+
+    }
+  } % end ANALYSES 
+
 } % end version 2.0-1
 
 \section{Changes in version 2.0-0}{
@@ -48,7 +82,7 @@
       
       \item Peter Minchin joins the \pkg{vegan} team.
       
-      \item \pkg{vegan} implements standard \R \code{NAMESPACE}. In
+      \item \pkg{vegan} implements standard \R \file{NAMESPACE}. In
       general, \code{S3} methods are not exported which means that you
       cannot directly use or see contents of functions like
       \code{cca.default}, \code{plot.cca} or \code{anova.ccabyterm}. To